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

    Neuronpedia

    INDEX
    Explanations

    references to temporal relationships or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.93
    ロウィン
    -0.90
    iſen
    -0.86
    ﹧
    -0.83
    ंदीखरीदारी
    -0.80
     ویکی‌پدی
    -0.80
    <unused43>
    -0.79
     Menſchen
    -0.79
    <unused42>
    -0.78
     المعيارى
    -0.78
    POSITIVE LOGITS
     fact
    0.82
     way
    0.73
     entanto
    0.67
     moment
    0.66
     times
    0.64
     first
    0.55
     case
    0.55
    прочем
    0.53
     indeed
    0.53
     vezes
    0.51
    Act Density 0.792%

    No Known Activations