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

    Neuronpedia

    INDEX
    Explanations

    dates in different months

    oai_token-act-pair · gpt-3.5-turbo

    specific months and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     looph
    -0.65
    educ
    -0.64
    estern
    -0.63
    trak
    -0.61
    ceivable
    -0.61
     blat
    -0.60
    eln
    -0.60
    itutional
    -0.60
    keyes
    -0.60
     arrang
    -0.59
    POSITIVE LOGITS
     2018
    0.92
     2021
    0.89
     2017
    0.86
     2019
    0.85
    nard
    0.84
     2015
    0.80
     27
    0.79
    bug
    0.79
     29
    0.78
     Feb
    0.78
    Act Density 0.073%

    No Known Activations