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

    Neuronpedia

    INDEX
    Explanations

    references to specific decades in the 1960s and 1970s

    oai_token-act-pair · gpt-3.5-turbo

    references to specific decades and periods in history

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dise
    -0.73
    tis
    -0.72
    STON
    -0.70
    cit
    -0.69
    Vote
    -0.69
    BIL
    -0.69
    viol
    -0.68
     Votes
    -0.68
    jury
    -0.67
    Marcus
    -0.67
    POSITIVE LOGITS
     twenties
    1.20
     early
    1.09
     1990
    1.04
     1980
    1.03
    ixties
    1.03
     1970
    1.03
     1960
    0.99
     1950
    0.92
     mid
    0.90
     90
    0.86
    Act Density 0.088%

    No Known Activations