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

    Neuronpedia

    INDEX
    Explanations

    dates in the format month day

    oai_token-act-pair · gpt-3.5-turbo

    references to the month of August

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nces
    -0.86
    kef
    -0.78
    arantine
    -0.78
     cumbers
    -0.77
    uden
    -0.76
    andem
    -0.74
    mercial
    -0.70
    Interstitial
    -0.70
    kefeller
    -0.68
    itton
    -0.68
    POSITIVE LOGITS
     2018
    1.07
    bugs
    1.05
     2017
    1.02
    sburg
    0.97
    bug
    0.96
     2016
    0.94
    mented
    0.94
     2015
    0.93
     Aug
    0.92
     2021
    0.91
    Act Density 0.024%

    No Known Activations