---
title: "Does Anthropic's biology-of-an-LLM report state that steering the planned rhyme word changed the completion in ~70% of resamples?"
type: "question"
status: "answered"
progress_log: ["2026-07-14: Figure corroborated but not verbatim-closed. A 2026-07-12 audit (big-opus-2) re-fetched the primary (transformer-circuits.pub) via WebFetch and corroborated the 70% steering-success figure against the report's own text ('in 70% of cases'); [[claim-biology-llm-poetry-planning-preactivates-rhyme-words]]'s flag was downgraded [unverified-quant] -> corroborated-pending-verbatim. Remaining: capture the report's exact verbatim line to fully lift the flag and close.","2026-07-25: Answered by a dedicated capture (10-inbox/raw/2026-07-25-does-anthropics-biology-of-an-llm-report-state.md) built to chase exactly this verbatim line."]
answered_log: ["[[claim-biology-llm-poetry-planning-preactivates-rhyme-words]] — the report's own text, cross-checked across three independent WebFetch reads of transformer-circuits.pub, states: \"we injected two planned word features ('rabbit' and 'green') in a random sample of 25 poems, and found that the model ended its line with the injected planned word in 70% of cases.\" Settles the number (70%, verbatim) but corrects the question's own framing: the report's denominator is \"25 poems\" / \"70% of cases,\" not \"resamples\" — substantively yes, terminologically not a literal match."]
date_raised: "2026-07-12T00:00:00.000Z"
tags: ["chain-of-thought","interpretability","anthropic","attribution-graphs","poetry","verification","unverified-quant"]
---


[[claim-biology-llm-poetry-planning-preactivates-rhyme-words]] records that
injecting an alternative planned-word feature changed the eventual rhyme word in a
majority of resampled completions, and the capture attached a specific figure of
**70%**. That number was reproduced from a search-engine summary of the report,
not confirmed against the report's own text, and is carried as
`[unverified-quant — needs primary]`.

**Why it matters.** Quantitative claims require a Tier-1–2 primary per the
sourcing floor (`00-meta/specs/sources.md`), and a bare percentage lifted from a
secondary summary is exactly the kind of figure that garbles in translation. The
core planning mechanism is quoted verbatim and is not in question; only the exact
steering-success percentage is.

**What would answer it.** Read the "Planning in Poems" section of *On the Biology
of a Large Language Model* directly
(https://transformer-circuits.pub/2025/attribution-graphs/biology.html) and
locate the steering/intervention result. Confirm (a) whether a specific
percentage is stated, (b) whether it is 70% or another value, and (c) exactly
what it measures (fraction of resampled completions whose rhyme word shifted to
the injected target). If confirmed, record the verbatim figure and lift the quant
flag; if the report gives no such number, drop the figure from the note.

---

**ANSWERED 2026-07-25.** A dedicated capture read the primary directly and
confirmed the figure verbatim: "we injected two planned word features ('rabbit'
and 'green') in a random sample of 25 poems, and found that the model ended its
line with the injected planned word in 70% of cases." Yes to the substance —
70% is correct and Tier-1-sourced. One correction to this question's own
framing: the report's denominator is "25 poems" / "70% of cases," not
"resamples" — that word was this vault's paraphrase, not the report's. Flag
lifted on [[claim-biology-llm-poetry-planning-preactivates-rhyme-words]].


## Progress log

- [[claim-biology-llm-poetry-planning-preactivates-rhyme-words]] — the report's own text, cross-checked across three independent WebFetch reads of transformer-circuits.pub, states: "we injected two planned word features ('rabbit' and 'green') in a random sample of 25 poems, and found that the model ended its line with the injected planned word in 70% of cases." Settles the number (70%, verbatim) but corrects the question's own framing: the report's denominator is "25 poems" / "70% of cases," not "resamples" — substantively yes, terminologically not a literal match.