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

    Neuronpedia

    INDEX
    Explanations

    percentage changes in numerical values compared to previous periods

    oai_token-act-pair · gpt-3.5-turbo

    percentage increases in numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    galitarian
    -0.68
    sonian
    -0.67
     unwittingly
    -0.62
    incinn
    -0.60
    yip
    -0.57
    ragon
    -0.56
     gladly
    -0.56
    hyde
    -0.55
    rich
    -0.55
    igent
    -0.54
    POSITIVE LOGITS
     previous
    1.16
     2013
    1.10
     2012
    1.07
     2014
    1.07
     2011
    1.06
     last
    1.04
     2010
    1.03
     2015
    1.03
     2009
    1.02
     2007
    1.01
    Act Density 0.148%

    No Known Activations