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

    Neuronpedia

    INDEX
    Explanations

    references to duration and time-related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     month
    -0.31
     Month
    -0.31
     year
    -0.30
    year
    -0.29
     Year
    -0.27
     Months
    -0.27
     Monthly
    -0.27
    month
    -0.27
    Month
    -0.26
    years
    -0.26
    POSITIVE LOGITS
     hours
    0.59
     Hours
    0.52
     overnight
    0.50
    Hours
    0.47
    hours
    0.43
    -hours
    0.41
     day
    0.39
    24
    0.39
     Overnight
    0.38
     Stunden
    0.38
    Act Density 0.036%

    No Known Activations