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

    Neuronpedia

    INDEX
    Explanations

    references to durations of time

    oai_token-act-pair · gpt-3.5-turbo

    numerical expressions related to time and duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Caption
    -0.70
    igation
    -0.63
     guid
    -0.62
    senal
    -0.61
    uria
    -0.59
     Strait
    -0.59
     Indust
    -0.59
    ãĤ¦
    -0.59
     Kun
    -0.59
     Hilbert
    -0.59
    POSITIVE LOGITS
     years
    0.98
    teenth
    0.96
     bucks
    0.94
    yrs
    0.91
     thousand
    0.88
    teen
    0.87
    aciously
    0.87
     cents
    0.86
    ciating
    0.85
     weeks
    0.84
    Act Density 0.417%

    No Known Activations