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

    Neuronpedia

    INDEX
    Explanations

    arguments or statements about social issues and public policy

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tycoon
    -0.87
    sheets
    -0.80
    oak
    -0.78
    abad
    -0.76
     Sins
    -0.73
    icles
    -0.73
    ouses
    -0.72
    anners
    -0.69
    bos
    -0.68
    sters
    -0.68
    POSITIVE LOGITS
     nonexistent
    1.01
     fatal
    0.88
     insur
    0.85
     outright
    0.83
     irre
    0.82
     nonex
    0.81
     undet
    0.79
     overwhelming
    0.79
     insign
    0.78
     unrecogn
    0.77
    Act Density 0.112%

    No Known Activations