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

    Neuronpedia

    INDEX
    Explanations

    dates and locations

    oai_token-act-pair · gpt-3.5-turbo

    comma placements in written dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.68
     streng
    -0.68
     predec
    -0.64
    ioned
    -0.62
    ldon
    -0.62
     citiz
    -0.61
     germ
    -0.58
     residue
    -0.58
    eton
    -0.57
     wasteland
    -0.57
    POSITIVE LOGITS
     2018
    1.37
     2017
    1.35
     2014
    1.30
     2015
    1.26
     2013
    1.24
     2016
    1.24
     2012
    1.19
     2011
    1.14
     2010
    1.13
     2009
    1.12
    Act Density 0.064%

    No Known Activations