INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ter
    -0.71
     Coz
    -0.65
    ustin
    -0.62
    ดิ
    -0.62
    Bundle
    -0.60
    เปล
    -0.59
     Spek
    -0.59
    Cor
    -0.58
    cor
    -0.58
     Dure
    -0.58
    POSITIVE LOGITS
     Congress
    1.14
     congress
    1.10
    congress
    1.09
     Fox
    1.07
     FOX
    1.03
     CONGRESS
    1.00
    Fox
    1.00
    Congress
    0.99
    fox
    0.99
     fox
    0.88
    Act Density 0.030%

    No Known Activations