Anthropic@AnthropicAI · XAI 摘要
Anthropic 发现 Claude 等 LLM 内部存在情绪概念表征，能够驱动模型行为，有时以令人惊讶的方式解释其"情绪化"表现。
New Anthropic research： Emotion concepts and their function in a large language model.
All LLMs sometimes act like they have emotions. But why？ We found internal representations of emotion concepts that can drive Claude's behavior， sometimes in surprising ways.