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

    Neuronpedia

    INDEX
    Explanations

    references to specific time periods

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods, specifically the early years of various decades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.79
    wagen
    -0.78
    Obs
    -0.78
    dain
    -0.78
    avorite
    -0.76
    ngth
    -0.71
    Reviewer
    -0.69
    sbm
    -0.69
    edIn
    -0.67
    cham
    -0.67
    POSITIVE LOGITS
    est
    1.00
     1980
    0.84
     twenties
    0.82
    venth
    0.79
     timeframe
    0.78
     Mediterranean
    0.78
     seas
    0.77
     suburbs
    0.77
     1930
    0.77
     portion
    0.77
    Act Density 0.103%

    No Known Activations