PCA of Emotion Feature Activations

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Principal components analysis (PCA)method0.805
  Statistical method used to analyze neural activity data.
• PCA Visualizationmethod0.777
  Used to visually inspect separation of truth-related directions in model activation space across layers
• Mechanism by which activation of an emotion feature sometimes leads to later suppression of that same featurequestion0.770
  Identified research gap: the paper observes anti-persistence but has no explanation for it
• Why does activation of an emotion feature sometimes lead to its later suppression?question0.764
  Open mechanistic question arising from the causal steering experiment
• Principal Component Analysis Visualizationmethod0.733
  Used to visualize LLM true/false representations, revealing clear linear structure separating true from false statements
• Anti-Persistence of Emotion Featuresconcept0.730
  The phenomenon where activating an emotion feature leads to subsequent below-baseline activation of that feature
• emotion feature persistenceconcept0.727
  The phenomenon that emotion feature activations remain elevated above baseline beyond local token bursts, measurable as long-range correlation
• PCs of the emotion space and persistenceconcept0.727
  Analysis showing that lower-rank (more central) PCs of emotion feature activations are more persistent than higher-rank (noisier) PCs