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, specifically the occurrences of the word "November" followed by a number

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jriwal
    -0.82
    gypt
    -0.78
    Reviewer
    -0.73
    ldon
    -0.73
     cumbers
    -0.72
    andem
    -0.70
    pires
    -0.69
     diaper
    -0.69
     gifted
    -0.69
    keyes
    -0.69
    POSITIVE LOGITS
     2015
    0.98
     2014
    0.96
     2017
    0.95
     2018
    0.95
     2016
    0.95
     2012
    0.92
     2013
    0.92
     November
    0.90
     2010
    0.89
     2011
    0.87
    Act Density 0.012%

    No Known Activations