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

    Neuronpedia

    INDEX
    Explanations

    time durations mentioned in terms of days, weeks, or months

    oai_token-act-pair · gpt-3.5-turbo

    quantities related to durations and counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anka
    -0.67
    ragon
    -0.66
    rike
    -0.65
     Caption
    -0.64
    clair
    -0.63
    rade
    -0.63
    agall
    -0.62
    agame
    -0.61
    artisan
    -0.61
     Discuss
    -0.61
    POSITIVE LOGITS
     reasons
    1.44
     consecutive
    1.33
     hours
    1.26
     weeks
    1.25
     years
    1.24
     months
    1.23
     purposes
    1.21
    straight
    1.19
     days
    1.17
     nights
    1.11
    Act Density 0.090%

    No Known Activations