Why were interventions with mass-mean probe directions extracted from the likely dataset so effective, despite these probes not being accurate at classifying true/false statements?

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

• Mass-mean probe directions outperform LR and CCS in causal intervention experiments (NIE) in 7/8 experimental conditionsfinding0.840
  Core result showing MM is superior to LR for causal implication despite similar classification accuracy
• Why did mass-mean probing with cities+neg_cities perform poorly for the 70B model, despite mass-mean probing with larger_than+smaller_than performing well?question0.808
  Unexplained result pointing to asymmetry in how training on opposites affects truth probes at 70B scale
• Why did mass-mean probing with cities+neg_cities training data perform poorly for the 70B model, despite larger_than+smaller_than performing well?question0.800
  Open question about scale-dependent asymmetry in training data effects
• If steering in a purported concept direction does not shift self-report in the expected direction, probe quality becomes suspect, especially when conventional probe metrics alone looked acceptable.quote0.793
  Key methodological insight: introspection enables a new probe validation criterion beyond conventional separation metrics
• Probe-based data attribution effectively reduces harmful behaviors via data interventionsclaim0.791
  Authors' central interpretive assertion that their method meaningfully mitigates unwanted behaviors.
• Probes trained on the likely dataset perform worse than chance on datasets with anti-correlations between text probability and truthfinding0.790
  Shows that truth representations are not reducible to text probability representations
• We hypothesize that explicitly instructing the model to evaluate the correctness of the given statement may change the geometry of truth directions.hypothesis0.790
  Motivating hypothesis for Section 5's investigation of prompt template effects.
• Accuracy does not vary linearly with latent reflection directions; instead it follows a more non-linear mapping that requires deeper theoretical treatment.claim0.779
  Theoretical limitation identified by the authors distinguishing reflection from stylistic tasks.