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

    Neuronpedia

    INDEX
    Explanations

    ordinal numbers indicating time frames

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods or durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.85
     seiz
    -0.64
    aimon
    -0.64
    unal
    -0.60
    geist
    -0.59
    vine
    -0.59
    igmat
    -0.59
     mathemat
    -0.58
    oki
    -0.58
    eret
    -0.58
    POSITIVE LOGITS
     months
    1.74
     weeks
    1.69
     years
    1.62
    months
    1.62
    years
    1.41
     decades
    1.38
     days
    1.35
     decade
    1.31
     Months
    1.31
     YEAR
    1.30
    Act Density 0.213%

    No Known Activations