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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical exponents and scaling laws

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    awtextra
    -0.92
     Sams
    -0.73
     Samar
    -0.68
     فريبيس
    -0.68
     Marcin
    -0.67
     Damas
    -0.66
    Colle
    -0.66
     Borja
    -0.65
    httphttps
    -0.64
    ialis
    -0.61
    POSITIVE LOGITS
     exponents
    1.58
     exponent
    1.55
    Exponent
    1.55
    exponent
    1.30
    ponents
    0.92
    ponent
    0.86
     expon
    0.85
     Exposition
    0.79
    Exposition
    0.75
     Núñez
    0.74
    Act Density 0.003%

    No Known Activations