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

    Neuronpedia

    INDEX
    Explanations

    function argument definitions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ARGUMENT
    -0.86
    logenetic
    -0.84
    tagHelperRunner
    -0.80
    )");
    -0.80
    oredCriteria
    -0.79
     Monfieur
    -0.78
    erent
    -0.77
     
    -0.77
     itſelf
    -0.76
     GetEnumerator
    -0.75
    POSITIVE LOGITS
     Elis
    0.76
     Sark
    0.68
     ویکی‌پدیا
    0.65
     arg
    0.64
     Krak
    0.63
    arg
    0.62
     Zha
    0.60
    argb
    0.59
     واح
    0.58
    jątk
    0.57
    Act Density 0.003%

    No Known Activations