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

    Neuronpedia

    INDEX
    Explanations

    patterns related to work schedules and time durations

    oai_token-act-pair · gpt-3.5-turbo

    temporal phrases and references to time management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wrongly
    -0.79
     counterfeit
    -0.75
     jaws
    -0.74
     unfairly
    -0.71
    wikipedia
    -0.69
     angered
    -0.69
     malice
    -0.68
     Lange
    -0.68
     resemb
    -0.67
     errone
    -0.67
    POSITIVE LOGITS
    weekly
    1.38
     weekends
    1.33
     weekly
    1.31
     evenings
    1.26
     monthly
    1.25
     fortnight
    1.21
     yearly
    1.17
    aturdays
    1.16
     Saturdays
    1.12
     sessions
    1.09
    Act Density 0.586%

    No Known Activations