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

    Neuronpedia

    INDEX
    Explanations

    phrases related to concepts of absurdity and seriousness

    oai_token-act-pair · gpt-3.5-turbo

    references to absurdity and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orthy
    -0.96
    bernatorial
    -0.72
    erion
    -0.72
    otti
    -0.71
    monton
    -0.71
    ener
    -0.70
    erella
    -0.70
    rection
    -0.69
    hips
    -0.69
    arten
    -0.69
    POSITIVE LOGITS
     humankind
    0.79
     capitalism
    0.77
     mankind
    0.77
     masculinity
    0.75
     existence
    0.75
     nature
    0.74
     these
    0.74
     liberalism
    0.71
     Zionism
    0.70
     circumstance
    0.70
    Act Density 0.222%

    No Known Activations