Net detection signal (detection minus control) is near-zero across all 40 layer-strength configurations: mean = -0.01 ± 0.03 logits

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

• At layer 0 α=5, detection-adjusted logit difference is +3.19 and control increase is +3.22, a difference of only 0.03 logitsfinding0.819
  Concrete numerical example showing detection and control are nearly identical at peak apparent accuracy
• Correlation r=0.999 between detection-adjusted logit difference and control logit increase across all 40 layer-strength configurationsfinding0.799
  Key quantitative evidence that detection signal is identical to global logit shift confound
• Binary detection adjusted accuracy reaches 97.3% at layer 0 with α=5 before baseline control is appliedfinding0.786
  The misleadingly high result that prior paradigm would report as evidence of introspection
• Binary detection accuracy (up to 97.3% at L0 α=5) is entirely explained by global logit shifts (r=0.999 correlation with control)finding0.768
  Core negative result: the binary detection paradigm cannot distinguish genuine introspection from uniform output bias
• Thought detection peaks at ~2/3 layer depth; intention checking peaks at ~1/2 layer depth.finding0.749
  Lindsey (2026) differential layer performance explained by Janus's path combinatorics — different tasks use different path distributions.
• Peak layer ℓ* median 10, IQR 0.384finding0.744
  Median layer where S(ℓ) peaks, across seeds.
• Math/code tasks S ≈ -1.65 at layers 8–12finding0.732
  Task-specific peak anchoring score for structured reasoning domains.
• Mean-difference patching in a two-layer ReLU circuit flips the decision to class-A by activating a third hidden unit that is silent for all natural class-A inputsfinding0.731
  Synthetic theoretical example showing pernicious divergence via hidden pathway activation