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

    Neuronpedia

    INDEX
    Explanations

    the beginning of paragraphs or sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bre
    -0.72
    vânt
    -0.71
    anz
    -0.71
    Bre
    -0.69
    Slf
    -0.66
    مس
    -0.66
    ={`
    -0.64
    fällt
    -0.63
    Aber
    -0.61
     Loch
    -0.61
    POSITIVE LOGITS
     Wiley
    1.55
    Wiley
    1.47
     Newcastle
    0.94
    )";
    0.90
     Coyote
    0.83
     nahilalakip
    0.83
    Newcastle
    0.83
     ویکی‌پدیای
    0.82
    Kite
    0.82
     Kite
    0.81
    Act Density 0.031%

    No Known Activations