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

    Neuronpedia

    INDEX
    Explanations

    dates

    oai_token-act-pair · gpt-3.5-turbo

    dates, particularly in the month of October

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istani
    -0.69
    inances
    -0.66
    ebook
    -0.66
    king
    -0.65
    Reviewer
    -0.65
    arantine
    -0.64
    ever
    -0.63
    inent
    -0.62
    emort
    -0.61
    trak
    -0.61
    POSITIVE LOGITS
     Surprise
    1.03
     2018
    0.97
    avia
    0.89
     2014
    0.88
     2017
    0.88
     2015
    0.87
    Aug
    0.85
     2016
    0.85
    flower
    0.83
     November
    0.83
    Act Density 0.015%

    No Known Activations