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

    Neuronpedia

    INDEX
    Explanations

    dates mentioned in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    dates in the format of month followed by day and year

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.99
     denomin
    -0.73
     cumbers
    -0.73
    igham
    -0.73
    unc
    -0.71
    Þ
    -0.71
    inctions
    -0.68
    trak
    -0.68
    ozyg
    -0.67
    achus
    -0.67
    POSITIVE LOGITS
    bug
    0.90
    flower
    0.88
     2015
    0.85
     2017
    0.84
    nard
    0.84
     2018
    0.82
     2014
    0.81
     2016
    0.78
     2013
    0.77
    teenth
    0.77
    Act Density 0.018%

    No Known Activations