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

    Neuronpedia

    INDEX
    Explanations

    dates or specific days of the week associated with significant events

    oai_token-act-pair · gpt-3.5-turbo

    references to specific days, particularly those associated with events or holidays

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Magn
    -0.73
    ocative
    -0.69
    ocal
    -0.68
    ran
    -0.68
    UTF
    -0.67
    Lear
    -0.67
    ynt
    -0.67
     streng
    -0.67
    ailable
    -0.66
     mathemat
    -0.66
    POSITIVE LOGITS
     festivities
    1.05
     weekend
    0.93
     Madness
    0.93
     2019
    0.87
     2017
    0.87
     anniversary
    0.86
     Massacre
    0.86
     2018
    0.85
     weekends
    0.83
     holidays
    0.83
    Act Density 0.089%

    No Known Activations