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

    Neuronpedia

    INDEX
    Explanations

    variable assignments in mathematical expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    سية
    -0.60
    GenerationType
    -0.60
     Tha
    -0.60
    namb
    -0.60
    bub
    -0.59
    IConfiguration
    -0.59
     Ruf
    -0.59
    swt
    -0.59
    #
    -0.59
    чатый
    -0.58
    POSITIVE LOGITS
    évaluateur
    1.01
     ostavi
    0.85
     désolés
    0.79
    oscar
    0.77
     fédéral
    0.77
     uve
    0.77
     Castor
    0.75
     Garuda
    0.75
     Varan
    0.73
     Biele
    0.69
    Act Density 0.053%

    No Known Activations