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

    Neuronpedia

    INDEX
    Explanations

    dates in the format "Month Day, Year" or similar date related information

    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
    -0.63
    ioned
    -0.61
     predec
    -0.60
     residue
    -0.58
    erred
    -0.57
     seam
    -0.56
     traced
    -0.56
    etheless
    -0.56
     bom
    -0.56
     attachments
    -0.56
    POSITIVE LOGITS
     2018
    1.39
     2017
    1.36
     2014
    1.27
     2015
    1.26
     2016
    1.23
     2013
    1.21
     2012
    1.15
     2011
    1.12
     2010
    1.11
     2009
    1.10
    Act Density 0.052%

    No Known Activations