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

    Neuronpedia

    INDEX
    Explanations

    mentions of being in a particular career or profession for a significant amount of time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating duration or the state of being in a particular context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Percent
    -0.71
     ILCS
    -0.68
    ollah
    -0.65
     congr
    -0.59
    é¾į
    -0.58
    .$
    -0.57
     Laurent
    -0.56
    Gray
    -0.54
     Denis
    -0.54
    #$
    -0.54
    POSITIVE LOGITS
     awhile
    0.95
     since
    0.74
    since
    0.71
    owan
    0.67
     intermitt
    0.63
     continuously
    0.62
    eat
    0.62
    iment
    0.62
    ãĤ¶
    0.61
     spor
    0.61
    Act Density 0.190%

    No Known Activations