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

    Neuronpedia

    INDEX
    Explanations

    references to specific lengths of time, such as years

    oai_token-act-pair · gpt-3.5-turbo

    references to durations of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rium
    -0.70
    ansk
    -0.63
    atta
    -0.63
    lycer
    -0.63
    linger
    -0.61
    detail
    -0.61
     Emblem
    -0.59
    enez
    -0.58
     Pose
    -0.55
     Apostle
    -0.55
    POSITIVE LOGITS
     years
    1.74
    years
    1.48
    yrs
    1.45
     YEAR
    1.40
     Years
    1.35
     yr
    1.17
    Years
    1.17
     months
    1.08
     generations
    1.04
     decades
    1.02
    Act Density 0.105%

    No Known Activations