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

    Neuronpedia

    INDEX
    Explanations

    numeric values related to various performance metrics or parameters

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Diſ
    -0.84
     Majefty
    -0.83
     Theſe
    -0.82
     myſelf
    -0.82
     Jefus
    -0.81
     theſe
    -0.79
     becauſe
    -0.77
     itſelf
    -0.77
     Conſ
    -0.77
     Reſ
    -0.77
    POSITIVE LOGITS
    IsContent
    0.57
    iffa
    0.54
    AnimationsModule
    0.49
     חיצוניים
    0.49
     ge
    0.46
     Nev
    0.44
     cellpadding
    0.44
     tre
    0.43
     bu
    0.42
     part
    0.42
    Act Density 0.030%

    No Known Activations