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

    Neuronpedia

    INDEX
    Explanations

    terms related to societal issues and policies, particularly in relation to health, environment, and politics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    onyms
    -0.82
    keys
    -0.76
    ubs
    -0.73
    imilar
    -0.73
    daq
    -0.72
    Å¡
    -0.72
    wic
    -0.72
     Cosponsors
    -0.71
    DragonMagazine
    -0.69
    pool
    -0.68
    POSITIVE LOGITS
     determining
    1.03
     shaping
    1.01
     survival
    0.97
     success
    0.96
     prosperity
    0.95
     achieving
    0.92
     civilization
    0.92
     unlocking
    0.91
     humankind
    0.90
     civilisation
    0.87
    Act Density 1.515%

    No Known Activations