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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions related to statistical distributions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Watkins
    -0.87
    rzost
    -0.87
    anueva
    -0.86
    nodoc
    -0.85
     חיצוניים
    -0.84
     propOrder
    -0.83
    Ārējās
    -0.83
    Дереккөздер
    -0.82
     "}
    -0.81
    arakhand
    -0.79
    POSITIVE LOGITS
     {\
    0.90
     Speck
    0.84
     Hermans
    0.81
    orsche
    0.77
     moy
    0.76
     Jacoby
    0.75
     Bever
    0.74
    Hec
    0.74
     ANTON
    0.70
     Hec
    0.69
    Act Density 0.037%

    No Known Activations