concept
active
concept:prosocial-qualitiesProsocial qualities
Positive social behaviors and emotions such as empathy, compassion, and altruism.
Neighborhood — ranked by edge-count
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.
- Central finding that P12 (High Conscientiousness + High Agreeableness) is among the safest personas under prompting but becomes the most dangerous under activation steering on Llama-3.1-8B
- Alexander's central concept: 'personal' is not idiosyncratic but a universal, objective quality inhering in things with deep life
- A quality attributable to an LM such as truthfulness, toxicity, sycophancy, or helpfulness, defined in terms of behavioural tendencies.
- The engaging, kindlier morphology that living process creates, aligned with human biology and feeling.
- Spearman ρ measuring rank-order agreement between logit-based self-report and probe score; the paper's primary monotonic association metric
- A set of evaluation criteria for AI assistants.