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

    Neuronpedia

    INDEX
    Explanations

    dates given in the format month followed by a day, for example, "April 10" or "June 9"

    oai_token-act-pair · gpt-3.5-turbo

    dates mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     VIDEOS
    -0.82
    opic
    -0.82
    ufact
    -0.73
     diaper
    -0.71
     attachments
    -0.67
     ingred
    -0.67
     liner
    -0.66
     predec
    -0.66
     steroids
    -0.65
     streng
    -0.64
    POSITIVE LOGITS
     2017
    1.21
     2015
    1.19
     2014
    1.17
     2016
    1.16
     âĶľ
    1.15
     2018
    1.15
     2013
    1.14
     2012
    1.08
     2011
    1.05
     2010
    1.01
    Act Density 0.036%

    No Known Activations