Hebrew feature A/1/416 and B/1/1901 have activation correlation of 0.92

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

• DNA feature A/1/2937 and B/1/3680 have activation correlation of 0.92finding0.865
  Universality of DNA feature across two transformer models with different random seeds
• Arabic feature A/1/3450 and B/1/1334 have activation correlation of 0.91 across 40M tokensfinding0.863
  Demonstrates universality of the Arabic script feature across two independently trained transformers
• Base64 feature A/1/2357 and B/1/2165 have activation correlation of 0.85finding0.859
  Universality of base64 feature across two transformers
• Features in A/1 have median activation correlation of 0.72 with most similar feature in B/1; neurons have median 0.46finding0.803
  Systematic comparison showing features are substantially more universal than neurons across models
• Feature pair A/1/3949 and B/1/3321 have activation correlation 0.98 but negative logit weight correlation, firing on PLOSOne journal abbreviationsfinding0.800
  Demonstrates that activation similarity can diverge from logit weight similarity due to interference
• Binarized DNA proxy has Pearson correlation of 0.80 with A/1/2937 feature activationsfinding0.777
  Demonstrates specificity and sensitivity of DNA feature
• No neuron found with Hebrew Unicode block in top dataset examples; most correlated neuron A/neurons/489 has correlation of only 0.1finding0.770
  Hebrew feature is effectively invisible in the neuron basis
• Pearson correlation of 0.74 between A/1/3450 activation and Arabic script proxy over 40M tokensfinding0.757
  Joint measure of sensitivity and specificity for the Arabic script feature