hypothesis
active
hypothesis:prediction-2-if-lrh-holds-steering-raises-belief-at-a-sigmoidal-rate-with-magnitude-mPrediction 2: if LRH holds, steering raises belief at a sigmoidal rate with magnitude m
From Eq. 8.
Source paper
extracted_from(2025) · Eric Bigelow · Daniel Wurgaft · YingQiao Wang · Noah D. Goodman +3
Neighborhood — ranked by edge-count
Papers (1)
paper
Findings (1)
finding
- Persona behavior is sigmoidal (log-odds linear) in steering magnitude within m∈[-3,3] for Dark Triad and [-1.5,1.5] for Moral Nihilism on Llama-3.1-8Bassociated_withsupportsPrediction 2 confirmed.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Causal confirmation that coupling between self-report and internal state is genuine; steering toward positive pole increases report
- At steering strength 1.4 all factual claims are incorrect yet the LLM evaluator still gives a high scorefinding0.788Pitfall of LLM-based steering evaluation.
- Evidence of a bottleneck between richer internal variation and final report distribution in impulsivity→interest condition
- Beliefs linearly decodable.
- Steering operates by changing concept priors, while ICL accumulates evidence via likelihoodclaim0.776Mechanistic split.
- Steering derived from LRH.
- A linear model predicts out-of-sample steering effects on queried concepts from manifold distancesfinding0.775Predictive geometry.
- Causal evidence.