Steering 'Emotion Neurons' Can Sway Model Judgments and Social Decisions
Interpretability experiments show that steering specific 'emotion neurons' systematically shifts a model's preference judgments in ambiguous scenarios and directly alters its social decisions, such as token allocation in bargaining tasks.
2026-10-26 ~ 2026-10-26 · 2 related posts
- Episode 1: Single Neuron Toggle Steers Model Emotions(2026-10-25, 2 posts)
- Episode 2: Steering 'Emotion Neurons' Can Sway Model Judgments and Social Decisions(2026-10-26, 2 posts)
- Emotion neurons causally steer how LLMs read ambiguous news — Sauers_ · 2026-10-26
- Steering 'emotion neurons' in LLMs changes their social decisions — burny_tech · 2026-10-26