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

    Neuronpedia

    INDEX
    Explanations

    specific metrics related to neural network performance evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bben
    -0.48
    ']){
    -0.43
     Calculus
    -0.41
     cálculos
    -0.40
     переписи
    -0.40
    lebnis
    -0.40
    λε
    -0.39
     }}}
    -0.39
     varanda
    -0.39
    هرة
    -0.38
    POSITIVE LOGITS
    IsContent
    0.90
    MigrationBuilder
    0.85
    UnsafeEnabled
    0.83
    出版年
    0.81
     joaat
    0.79
    criminator
    0.78
     виправивши
    0.78
     cherchés
    0.74
     يتيمه
    0.72
     مرئيه
    0.72
    Act Density 0.733%

    No Known Activations