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

    Neuronpedia

    INDEX
    Explanations

    numerical values

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ,”
    -0.57
    nonatomic
    -0.55
    risse
    -0.54
    reu
    -0.53
    %");
    -0.53
     cons
    -0.52
    sha
    -0.52
    chea
    -0.52
     sha
    -0.51
    yal
    -0.51
    POSITIVE LOGITS
     Erişim
    0.71
    NameInMap
    0.68
     '\\;'
    0.66
    例文帳に追加
    0.60
     ModelExpression
    0.60
     كومونز
    0.59
     "..\..\..\
    0.59
     oreilles
    0.58
     tapaht
    0.57
    ècie
    0.57
    Act Density 0.007%

    No Known Activations