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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, potentially related to sports or news

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    usher
    -0.85
    engers
    -0.77
     fri
    -0.71
    ibel
    -0.68
    Catal
    -0.67
    azar
    -0.66
     Archdemon
    -0.63
    inoa
    -0.62
    ossier
    -0.62
    artney
    -0.62
    POSITIVE LOGITS
     Ort
    0.81
    pheus
    0.81
    akov
    0.78
    anka
    0.76
    heastern
    0.72
    stall
    0.71
    yy
    0.70
    mond
    0.68
    craft
    0.67
    gdala
    0.67
    Act Density 11.422%

    No Known Activations