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

    Neuronpedia

    INDEX
    Explanations

    references to varieties or variations of things, specifically those indicated by "var" prefixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tail
    -0.20
    i
    -0.17
    iw
    -0.16
    est
    -0.15
    omics
    -0.15
    íĥĿ
    -0.15
     Schwe
    -0.15
    ury
    -0.14
    gage
    -0.14
    en
    -0.14
    POSITIVE LOGITS
    iances
    0.26
    iously
    0.22
    argout
    0.22
    iations
    0.21
    _dump
    0.21
    nish
    0.21
    adero
    0.20
    (--
    0.19
    ieg
    0.19
    iação
    0.19
    Act Density 0.026%

    No Known Activations