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

    Neuronpedia

    INDEX
    Explanations

    mentions of medical conditions or physical actions related to strokes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    %"
    -0.72
    guyen
    -0.72
    etheless
    -0.71
    itive
    -0.69
    ãĤ©
    -0.65
    rum
    -0.64
    essor
    -0.63
    gemony
    -0.61
    ilogy
    -0.61
    ities
    -0.61
    POSITIVE LOGITS
     stroke
    1.00
    manship
    0.97
     strokes
    0.86
    weed
    0.76
    stroke
    0.73
    teenth
    0.68
    aukee
    0.66
    fish
    0.66
    stem
    0.65
     Stro
    0.64
    Act Density 8.440%

    No Known Activations