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

    Neuronpedia

    INDEX
    Explanations

    information related to quantities, numbers, and statistics

    oai_token-act-pair · gpt-3.5-turbo

    references to specific time periods or data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.67
     ingred
    -0.65
    ella
    -0.64
    bol
    -0.63
    Alias
    -0.63
    HAEL
    -0.62
     disapp
    -0.61
     awa
    -0.60
    ALSE
    -0.60
    aye
    -0.58
    POSITIVE LOGITS
     2013
    1.45
     2014
    1.45
     2015
    1.41
     2011
    1.40
     2012
    1.39
     2010
    1.35
     2009
    1.33
     2016
    1.33
     2007
    1.30
     2006
    1.26
    Act Density 0.175%

    No Known Activations