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

    Neuronpedia

    INDEX
    Explanations

    adverbs that indicate quick action or response

    oai_token-act-pair · gpt-3.5-turbo

    adverbs indicating quickness or promptness in actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pel
    -0.82
    ammy
    -0.69
    aden
    -0.67
    artisan
    -0.67
    ramid
    -0.66
    oft
    -0.66
    ancy
    -0.65
    olen
    -0.64
    enezuel
    -0.64
    byn
    -0.64
    POSITIVE LOGITS
     promptly
    1.02
     thereafter
    0.88
    aneously
    0.86
     afterwards
    0.78
     afterward
    0.76
     ensued
    0.75
    entimes
    0.75
     ejac
    0.73
     responds
    0.72
     obliged
    0.71
    Act Density 0.004%

    No Known Activations