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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases and data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Months
    -0.71
     months
    -0.67
     weeks
    -0.62
    months
    -0.61
     month
    -0.57
    Weeks
    -0.57
     meses
    -0.56
     semanas
    -0.56
     years
    -0.54
    month
    -0.54
    POSITIVE LOGITS
     hour
    1.11
     hourly
    1.01
     HOUR
    0.97
     midday
    0.93
    hour
    0.92
     afternoon
    0.90
     hours
    0.89
     Stunde
    0.89
     Hour
    0.88
     Hourly
    0.88
    Act Density 0.423%

    No Known Activations