INDEX
    Explanations

    names of individuals, particularly those associated with political roles or public figures

    New Auto-Interp
    Negative Logits
    ibel
    -1.03
    oos
    -0.88
    pper
    -0.85
    ider
    -0.84
    vent
    -0.84
    ker
    -0.81
    ppers
    -0.80
    iframe
    -0.79
    icial
    -0.77
    ilage
    -0.75
    POSITIVE LOGITS
     GOODMAN
    0.80
    sburg
    0.78
     pudding
    0.77
     manuscripts
    0.76
     Divinity
    0.70
     Peck
    0.69
     XVI
    0.69
    Delivery
    0.67
     tigers
    0.67
     desserts
    0.65
    Act Density 0.044%

    No Known Activations