Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    numerical values or references related to statistics or measurements in a given context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numbers, particularly those that appear to be digits in phone numbers, patent numbers, or section/code references.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    numeric codes and identifiers (such as patent numbers, phone numbers, hexadecimal values, and reference codes).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     [{
    -0.39
     abut
    -0.37
    Annotation
    -0.37
    findpost
    -0.36
    Pyx
    -0.36
    adona
    -0.35
     Kuri
    -0.35
    jsonwebtoken
    -0.34
    annotation
    -0.34
    JspWriter
    -0.34
    POSITIVE LOGITS
    Datuak
    0.57
    MigrationBuilder
    0.50
    ✭✭
    0.49
    ImageContext
    0.48
    principalColumn
    0.46
     STAR
    0.45
     שוליים
    0.45
    STAR
    0.45
     nahilalakip
    0.45
     Numerade
    0.45
    Act Density 0.454%

    No Known Activations