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

    Neuronpedia

    INDEX
    Explanations

    references to the impact of various factors on society, systems, and priorities

    oai_token-act-pair · gpt-3.5-turbo

    themes related to societal issues and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ppa
    -0.75
    Yep
    -0.74
     rooft
    -0.68
    Tweet
    -0.67
     typo
    -0.66
    à
    -0.66
    VIDEO
    -0.66
     Goose
    -0.66
     kidding
    -0.65
     joke
    -0.64
    POSITIVE LOGITS
     arising
    0.88
     characterized
    0.84
     impair
    0.84
     therefore
    0.83
    alyses
    0.83
     embodiments
    0.82
     thereby
    0.80
     arise
    0.80
     develops
    0.79
     theoret
    0.79
    Act Density 0.944%

    No Known Activations