Steering affects type hint writing by modifying the model's belief about whether it is being evaluated, not by directly encoding type hint information

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

• Linear steering is often mismatched with a model's internal representation geometry, producing noisy, off-target effects.claim0.793
  The paper's critique of the standard linear steering baseline, supported by the days-of-week demo.
• Activation steering toward deployment reduces type hint rate to <11% even with Wood Labs evaluation cue presentfinding0.789
  Main result: steering elicits deployment behavior even when the evaluation cue is present and prompting fails.
• Inhibition steering produces larger accuracy drops than enhancement steering produces accuracy gains, across all models and datasets testedfinding0.783
  Key asymmetry finding: suppressing reflection is easier than inducing it.
• Steering's effect on verbalized chain-of-thought evaluation/deployment beliefs is a useful proxy for its effect on actual deployment behaviorclaim0.780
  Practical guidance for practitioners who lack ground-truth model organisms.
• The steering-sign test functions as a practical probe-validation criterion: inverted report changes when steering suspect probe qualityclaim0.777
  Methodological contribution: used to exclude focus-1B and impulsivity-8B from scaling analysis
• Steering at 6 layers (strength 0.6 each, total 3.6) outperforms single-layer steering at equivalent total strength for type hint suppressionfinding0.775
  Demonstrates distributed steering is more effective and less accuracy-damaging than concentrated steering.
• Activation steering effectively biases latent representations but does not fully replicate the mechanisms triggered by explicit instruction.claim0.774
  Nuanced interpretive claim about the limits of steering as a mechanism for reflection enhancement.
• Steering vectors discover effective triggers such as 'However' and 'Otherwise', consistent with prior reported reflection datasetsfinding0.774
  Validates that steering vectors capture reflection semantics by finding tokens reported in related work.