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

    Neuronpedia

    INDEX
    Explanations

    dates

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the month "October."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fman
    -0.81
    kus
    -0.73
    ps
    -0.69
    chers
    -0.68
    cius
    -0.67
    ggle
    -0.67
    cci
    -0.67
    pee
    -0.66
    cher
    -0.66
    ever
    -0.66
    POSITIVE LOGITS
     Surprise
    1.14
    fair
    0.86
     2014
    0.82
    avia
    0.82
     2015
    0.80
     2012
    0.78
    OB
    0.77
     2013
    0.76
     2017
    0.76
     2016
    0.76
    Act Density 0.020%

    No Known Activations