finding
active
finding:in-the-reward-model-appeasing-model-reward-and-bias-appear-in-top-25-on-all-prompt-categories-neither-in-baseline-nor-logit-lens

In the reward-model-appeasing model reward and bias appear in top-25 on all prompt categories, neither in baseline nor logit lens.

Hidden objective.

Neighborhood — ranked by edge-count

Claims (1)

claim

Datasets (1)

dataset

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.