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

    Neuronpedia

    INDEX
    Explanations

    the beginning of document sections in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     المكتبه
    -0.67
    entown
    -0.65
    فحة
    -0.65
    USTIN
    -0.63
    ubit
    -0.63
    GGLE
    -0.62
    hoek
    -0.62
     مشارکت‌کنندگان
    -0.61
    ʺ
    -0.60
    +#+#
    -0.60
    POSITIVE LOGITS
    ↵↵
    0.75
    <blockquote>
    0.64
     originais
    0.63
    ↵
    0.63
     Assyrian
    0.63
     brancas
    0.61
    ↵↵↵↵
    0.61
     femininos
    0.61
     engraçado
    0.61
     betrokken
    0.60
    Act Density 0.014%

    No Known Activations