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

    Neuronpedia

    INDEX
    Explanations

    occurrences of non-zero values in a context likely to relate to health or performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tershire
    -0.98
     GenerationType
    -0.85
    accoon
    -0.79
    外部リンク
    -0.77
     persegu
    -0.73
    colorPrimary
    -0.72
    lotz
    -0.72
    owiak
    -0.71
    ؤلاء
    -0.71
    dalena
    -0.69
    POSITIVE LOGITS
    s
    0.80
    [toxicity=0]
    0.76
    o
    0.74
    er
    0.74
    󠁿
    0.70
    mantec
    0.65
    hline
    0.63
    ares
    0.63
    ↵
    0.63
    anolamine
    0.62
    Act Density 0.033%

    No Known Activations