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

    Neuronpedia

    INDEX
    Explanations

    dates and times represented in the format of numbers

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     streng
    -0.66
    othe
    -0.64
     behavi
    -0.62
    erred
    -0.59
     fore
    -0.55
     germ
    -0.54
     appre
    -0.54
     predec
    -0.54
    VERTISEMENT
    -0.53
    ļéĨĴ
    -0.53
    POSITIVE LOGITS
     2017
    1.28
     2018
    1.28
     2015
    1.21
     2016
    1.18
     2014
    1.18
     2013
    1.17
     2011
    1.14
     2012
    1.13
     2010
    1.12
     2007
    1.11
    Act Density 0.069%

    No Known Activations