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

    Neuronpedia

    INDEX
    Explanations

    phrases related to changes in numerical data over time

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "in" along with numerical data related to time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ens
    -0.79
     ingred
    -0.69
    emo
    -0.67
     minded
    -0.65
     looms
    -0.64
    ById
    -0.62
    ALSE
    -0.62
    ATHER
    -0.62
    sonian
    -0.62
    onym
    -0.59
    POSITIVE LOGITS
     2009
    1.25
     2012
    1.24
     2013
    1.24
     2014
    1.24
     2011
    1.23
     2010
    1.21
     2008
    1.20
     2015
    1.20
     2007
    1.18
     2016
    1.15
    Act Density 0.156%

    No Known Activations