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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific individuals, locations, and organizations in news articles

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ickr
    -1.04
    Ô
    -1.04
    ĸļ
    -1.02
    mbuds
    -0.99
    isal
    -0.97
    ipedia
    -0.96
     Siber
    -0.95
    azeera
    -0.90
    endas
    -0.87
    atsuki
    -0.85
    POSITIVE LOGITS
     duo
    1.23
     lawmaker
    1.12
     mogul
    1.12
     retailer
    1.10
     politician
    1.09
     entrepreneur
    1.06
     titan
    1.06
     Frenchman
    1.04
     runner
    1.04
     autom
    1.04
    Act Density 1.710%

    No Known Activations