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

    Neuronpedia

    INDEX
    Explanations

    dates written with a comma followed by a number representing how certain that date is

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, specifically commas in dates and lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGR
    -0.66
     conc
    -0.65
     achievements
    -0.62
     enhancement
    -0.60
     abound
    -0.60
    ersed
    -0.60
     gad
    -0.59
    ãĤ¦ãĤ¹
    -0.59
    finder
    -0.58
    Recent
    -0.58
    POSITIVE LOGITS
     2018
    0.92
     2017
    0.89
    000
    0.87
     2016
    0.87
     2015
    0.85
     2014
    0.84
     2012
    0.83
     2010
    0.82
     2005
    0.80
     2006
    0.79
    Act Density 0.107%

    No Known Activations