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

    Neuronpedia

    INDEX
    Explanations

    dates (specifically in the format "April [day]")

    oai_token-act-pair · gpt-3.5-turbo

    references to specific dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebook
    -0.72
    atem
    -0.71
    perm
    -0.67
    estern
    -0.64
    keyes
    -0.64
    educ
    -0.62
    desc
    -0.62
     VIDEOS
    -0.62
    swick
    -0.61
    ROR
    -0.60
    POSITIVE LOGITS
     Fool
    0.99
     2015
    0.92
    flower
    0.92
     2018
    0.92
     2019
    0.91
     2017
    0.90
    eteenth
    0.86
     2014
    0.85
     2016
    0.83
    nard
    0.82
    Act Density 0.019%

    No Known Activations