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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating actions that are about to happen or need to happen

    oai_token-act-pair · gpt-3.5-turbo

    actions or events that are contingent upon previous occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.75
     notwithstanding
    -0.71
     dwar
    -0.68
     largeDownload
    -0.67
     contrasted
    -0.67
     contrasts
    -0.66
     discrep
    -0.64
    <?
    -0.63
     Nanto
    -0.63
     dolphin
    -0.61
    POSITIVE LOGITS
    ittal
    0.75
    uberty
    0.72
    adelphia
    0.70
    azeera
    0.68
    ilater
    0.68
    eming
    0.68
    acly
    0.67
    rehend
    0.67
    ividual
    0.67
     definitive
    0.66
    Act Density 0.231%

    No Known Activations