Causal Intervention on Representations

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

• How do interventions on representations causally steer behavior?question0.865
  Core question motivating the shift from linear to geometry-aware steering; answered via manifold alignment analysis.
• Causal Intervention via Activation Shiftingmethod0.833
  Method of shifting hidden state activations along probe directions to cause the model to treat false statements as true and vice versa; evaluated on OOD inputs
• Causal Intervention via Activation Shiftmethod0.825
  Intervening in model forward pass by adding/subtracting probe direction to group (b) hidden states to flip truth judgments
• causal shaping of behavior by representation geometryconcept0.816
  Central question: does geometry in activation space causally determine behavior?
• Intervention Propagationconcept0.803
  Property that additive modifications to activations affect all downstream computations, enabling tractable behavioral control
• Causal Mediationconcept0.791
  Whether an internal direction causally controls a target behavior, verified by intervention success
• Divergent representations are a common, if not likely, outcome of causal interventions across a wide range of methodsclaim0.790
  Core empirical claim of the paper supported by both theoretical proof and empirical demonstration
• Causal Influence Diagramsframework0.779
  Framework informing path-specific objectives by identifying causal chains leading to risky behaviors