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

    Neuronpedia

    INDEX
    Explanations

    keywords and phrases that indicate statistical or mathematical elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ennemis
    -0.57
     Infatti
    -0.56
    isela
    -0.55
     namelijk
    -0.54
     særlig
    -0.53
     küche
    -0.53
     compréhen
    -0.53
     espagne
    -0.52
     spesielt
    -0.52
     monasterio
    -0.51
    POSITIVE LOGITS
    <bos>
    2.47
    '
    1.16
    ’
    1.11
     Мексичка
    0.91
     виправивши
    0.90
     فريبيس
    0.89
     Савезне
    0.79
    AddTagHelper
    0.79
    begin
    0.78
     Paglinawan
    0.73
    Act Density 0.792%

    No Known Activations