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

    Neuronpedia

    INDEX
    Explanations

    quantitative expressions or terms related to mathematical operations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     extré
    -0.56
    mean
    -0.54
    /**/*.
    -0.53
     fuoco
    -0.53
    NOPQRST
    -0.50
     dientes
    -0.47
     avancée
    -0.47
    LookAnd
    -0.47
     résine
    -0.47
     étage
    -0.46
    POSITIVE LOGITS
     estekak
    0.71
     חיצוניים
    0.64
     bezeichneter
    0.64
    Izvori
    0.63
     nahilalakip
    0.62
    DeleteBehavior
    0.58
    сылкі
    0.58
    帖最后由
    0.58
    auré
    0.57
     שוליים
    0.56
    Act Density 0.003%

    No Known Activations