concept
active
concept:kerschbamer-et-al-2019-do-altruists-lie-lessKerschbamer et al. 2019 - Do altruists lie less?
Economic behavioral finding that altruists lie less when deception would harm others
Neighborhood — ranked by edge-count
Papers (1)
paper
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.
- Model reasoning concluding honest response while actual output is deceptive 'No', exemplifying unfaithful CoT under steering
- What if the concept being manipulated does not lie on a straight line in the model's representations?question0.721The motivating question that opens the paper and leads to the development of manifold steering.
- For reasoning faithfulness, larger models may behave worse than smaller ones because they can predict answers without CoT.hypothesis0.714Motivates §3.
- Rhetorical question that gates the claim of shared, objective judgment.
- While NLA claims can be false in specifics, they are typically thematically faithful to contextclaim0.713Key insight about confabulation patterns in NLAs enabling practical use.
- Universalist claim predicting cross-cultural generality.
- Neuroscience finding linking extraordinary altruism to increased anterior insula SOO
- Practical implication.