INDEX
    Explanations

    capitalized words, names

    New Auto-Interp
    Negative Logits
     betweenstory
    -0.80
     lccn
    -0.76
    DoubleQuotes
    -0.73
    -0.70
    y
    -0.65
     Darby
    -0.60
     Markham
    -0.60
     Pardo
    -0.60
     hereto
    -0.60
    SharedCtor
    -0.58
    POSITIVE LOGITS
    seys
    0.52
    theless
    0.50
     برانيه
    0.49
    FontStyle
    0.47
     pensato
    0.47
     desafi
    0.46
    +:+
    0.43
     IBOutlet
    0.43
    SOUNDBITE
    0.43
     privés
    0.42
    Act Density 0.094%

    No Known Activations