finding
active
finding:reward-hacking-65-with-calm-suppressed-falling-to-10-with-strong-positive-calm

Reward hacking ~65% with calm suppressed, falling to ~10% with strong positive calm

Calm protects.

Source paper

extracted_from
Emotion Concepts and their Function in a Large Language Model
(2026) · Nicholas Sofroniew · Isaac Kauvar · William Saunders · Runjin Chen +12

Neighborhood — ranked by edge-count

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.