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

    Neuronpedia

    INDEX
    Explanations

    dates written in the month-day format

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific dates, particularly in January

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     VIDEOS
    -0.71
    ographed
    -0.71
    atcher
    -0.67
    atic
    -0.65
    psc
    -0.62
    arms
    -0.62
    ropolitan
    -0.62
     diaper
    -0.61
    pn
    -0.61
    assium
    -0.61
    POSITIVE LOGITS
     2019
    0.99
    esville
    0.94
    iversary
    0.92
     2017
    0.92
    vier
    0.92
    ruary
    0.91
     2015
    0.86
     2021
    0.83
     Madness
    0.83
     2018
    0.83
    Act Density 0.025%

    No Known Activations