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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions, specifically durations like days, years, hours, and months

    oai_token-act-pair · gpt-3.5-turbo

    time-related quantities and durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥķãĤ©
    -0.66
    irie
    -0.66
     hypocr
    -0.65
     defe
    -0.63
     colle
    -0.59
    amara
    -0.56
     Punk
    -0.54
    gotten
    -0.54
     failings
    -0.54
    SHARE
    -0.53
    POSITIVE LOGITS
     intervals
    1.15
     increments
    1.12
     depending
    1.02
    depending
    1.00
     duration
    1.00
     elapsed
    1.00
     ago
    0.97
     apiece
    0.94
     consecut
    0.91
     periods
    0.90
    Act Density 0.138%

    No Known Activations