INDEX

Explanations

weigh importance

This neuron detects tokens that represent numeric or URL-like elements—e.g. years, volume/page numbers, and “https://” links often found in citations or references.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

๕

0.84

ছিলো

0.84

Valve

0.83

DefaultFor

0.81

CTG

0.81

'},

0.79

ছিল

0.78

ZX

0.77

 სახელმწიფო

0.76

ছিলাম

0.75

POSITIVE LOGITS

 spermatozoa

0.82

 estrogen

0.79



0.78

 tulle

0.77

い

0.75

≥

0.73

 cioc

0.70

ς

0.70

 roaming

0.70

Activations Density 0.001%