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

    Neuronpedia

    INDEX
    Explanations

    dates indicated in the month and day format

    oai_token-act-pair · gpt-3.5-turbo

    specific dates or mentions of the month of March

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cumbers
    -0.74
     unnecess
    -0.68
    ¥ŀ
    -0.66
    Reviewer
    -0.64
     eleph
    -0.63
    gone
    -0.62
     gifted
    -0.61
     neoc
    -0.61
     looph
    -0.61
     selective
    -0.61
    POSITIVE LOGITS
     Madness
    0.97
     2019
    0.96
     2015
    0.94
     2018
    0.93
     2017
    0.93
    flower
    0.86
     2016
    0.85
     2021
    0.85
     2013
    0.84
    nard
    0.84
    Act Density 0.031%

    No Known Activations