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

    Neuronpedia

    INDEX
    Explanations

    places and geographic locations

    oai_token-act-pair · gpt-3.5-turbo

    geographic names and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     censored
    -0.72
     superheroes
    -0.69
     Australians
    -0.68
     inexperienced
    -0.68
     governments
    -0.67
     feds
    -0.66
     CEOs
    -0.66
     reviewer
    -0.65
     editors
    -0.64
     Bezos
    -0.63
    POSITIVE LOGITS
    bah
    1.06
    qqa
    1.05
    unda
    1.01
    abad
    1.00
     Cemetery
    0.97
    ulla
    0.97
    raq
    0.96
    pora
    0.96
    ridor
    0.95
    ovo
    0.95
    Act Density 0.262%

    No Known Activations