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

    Neuronpedia

    INDEX
    Explanations

    urls

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Suc
    -0.71
    ertodd
    -0.71
    EY
    -0.70
     Luther
    -0.65
     Noir
    -0.65
    SPONSORED
    -0.64
    Guest
    -0.64
    ZA
    -0.63
     Sou
    -0.63
     Watt
    -0.62
    POSITIVE LOGITS
    itzer
    1.08
    itudinal
    1.03
    ough
    0.89
    itional
    0.89
    itude
    0.89
    gements
    0.85
    aston
    0.84
    ding
    0.83
    falls
    0.82
    uci
    0.79
    Act Density 0.022%

    No Known Activations