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

    Neuronpedia

    INDEX
    Explanations

    phrases related to timing and scheduled events

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    rénées
    -0.68
    urent
    -0.64
    NOPQRST
    -0.62
     Roskov
    -0.61
    osoba
    -0.59
    InitVars
    -0.57
     مرئيه
    -0.57
    verwijspagina
    -0.56
    Билгалдахарш
    -0.56
     reaction
    -0.55
    POSITIVE LOGITS
    何时
    0.60
     mijne
    0.58
     Whence
    0.58
     ſhe
    0.55
     Shakspeare
    0.54
    <thead>
    0.54
    testens
    0.53
     giustizia
    0.53
     schedules
    0.52
    什么时候
    0.52
    Act Density 0.019%

    No Known Activations