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

    Neuronpedia

    INDEX
    Explanations

    numerical intervals

    oai_token-act-pair · gpt-3.5-turbo

    terms related to statistical intervals and durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ongyang
    -0.74
    son
    -0.74
    ging
    -0.72
    gewater
    -0.71
    onom
    -0.71
    erald
    -0.70
    kie
    -0.70
    advertising
    -0.69
    ramid
    -0.67
    tty
    -0.67
    POSITIVE LOGITS
     intervals
    1.19
     interval
    1.09
     between
    0.81
     mund
    0.80
    cens
    0.77
     repeats
    0.73
     gratification
    0.72
    arella
    0.71
     periods
    0.68
    ftime
    0.67
    Act Density 0.010%

    No Known Activations