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

    Neuronpedia

    INDEX
    Explanations

    references to figures in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    WebElementEntity
    -0.88
     CreateTagHelper
    -0.76
     <<<<<<<<<<<<<<
    -0.72
     autorytatywna
    -0.71
     виправивши
    -0.71
    хьтан
    -0.66
    Rujuakan
    -0.65
    олові
    -0.64
     تضيفلها
    -0.64
    Hauptartikel
    -0.64
    POSITIVE LOGITS
     Pary
    0.57
    diente
    0.54
    használ
    0.53
     Steff
    0.52
     gw
    0.50
     Maiden
    0.50
    IVATE
    0.49
    lieder
    0.48
    palla
    0.48
     Garibaldi
    0.48
    Act Density 0.012%

    No Known Activations