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

    Neuronpedia

    INDEX
    Explanations

    quantitative performance metrics and comparisons in statistical or competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.66
    StructEnd
    -0.49
     noDo
    -0.49
     padx
    -0.48
    โย
    -0.48
    XMLSchema
    -0.48
     Hanley
    -0.47
     صوتيه
    -0.46
     Biôgrafia
    -0.46
    PreInfinity
    -0.46
    POSITIVE LOGITS
     autorytatywna
    0.66
     Damit
    0.62
    ostante
    0.61
    :✨
    0.60
     Soit
    0.59
    CloseOperation
    0.58
    Damit
    0.58
     ţ
    0.56
    trailing
    0.53
    isert
    0.53
    Act Density 0.277%

    No Known Activations