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

    Neuronpedia

    INDEX
    Explanations

    mathematical calculations and equations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.98
    Datuak
    -0.97
     ſever
    -0.92
     purpoſe
    -0.91
    -0.90
     Diſ
    -0.88
     ſche
    -0.87
     itſelf
    -0.85
     pleaſure
    -0.85
     Majefty
    -0.85
    POSITIVE LOGITS
    ierto
    0.52
     a
    0.52
     an
    0.50
     familiar
    0.49
     the
    0.48
    ,
    0.48
     A
    0.47
     extra
    0.47
     at
    0.47
     Le
    0.47
    Act Density 0.148%

    No Known Activations