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

    Neuronpedia

    INDEX
    Explanations

    dates represented in the format "Month Day"

    oai_token-act-pair · gpt-3.5-turbo

    dates in the month of June

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -1.09
    achus
    -0.79
    igham
    -0.79
     denomin
    -0.75
    acca
    -0.71
    rians
    -0.69
    unc
    -0.68
    ozyg
    -0.67
    amines
    -0.67
    uncle
    -0.66
    POSITIVE LOGITS
    bug
    0.88
    flower
    0.84
     2015
    0.83
     2017
    0.83
     2018
    0.79
    teenth
    0.79
     2014
    0.78
     2016
    0.77
     2013
    0.76
    nard
    0.75
    Act Density 0.019%

    No Known Activations