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

    Neuronpedia

    INDEX
    Explanations

    text formatting elements, specifically italics and bold

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rinfo
    -0.82
    arakhand
    -0.72
     Cowell
    -0.71
    GenerationType
    -0.69
     Drummond
    -0.69
     UND
    -0.68
    Географиясе
    -0.68
    ticultural
    -0.66
     Johnnie
    -0.66
     Marav
    -0.66
    POSITIVE LOGITS
    </em>
    1.50
    <em>
    1.40
    <i>
    1.30
    </i>
    1.18
    /*
    1.04
    possum
    0.90
    <u>
    0.88
    』『
    0.88
    icordia
    0.88
    hyr
    0.88
    Act Density 0.017%

    No Known Activations