finding
active
finding:post-training-raises-brooding-reflective-gloomy-vulnerable-activations-and-lowers-playful-exuberant-spiteful-enthusiasticPost-training raises brooding, reflective, gloomy, vulnerable activations and lowers playful, exuberant, spiteful, enthusiastic
Shift toward low arousal, low valence.
Source paper
extracted_from(2026) · Nicholas Sofroniew · Isaac Kauvar · William Saunders · Runjin Chen +12
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Interpretation of shifts.
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.
- Different post-training strategies substantially influence introspection task performance; 'helpful-only' variants show higher false positives but some achieve strong net performance.
- Assertion about the role of post-training in eliciting introspection.
- Finding that base models have high false positives and no net positive performance.
- Base pretrained models show high false positive rates and achieve no net task performance on concept injection detection; post-training essential for introspection.
- Central interpretive claim and motivation for future work
- Authors' interpretive endorsement of PSM view, backed by transfer experiments
- Context-independent transformation.
- Load-bearing summary of the paper's core finding about persona stability