INDEX
    Explanations

    references to various football leagues, particularly the AFL and NFL

    New Auto-Interp
    Negative Logits
    ilde
    -0.15
     KIND
    -0.15
     Xiao
    -0.15
    stav
    -0.14
     lekker
    -0.14
    Clark
    -0.14
    nga
    -0.14
    κÎŃ
    -0.13
     Incontri
    -0.13
    ningen
    -0.13
    POSITIVE LOGITS
    ubits
    0.18
    olu
    0.15
    rices
    0.15
    ignon
    0.14
     Mour
    0.14
    endar
    0.14
    credentials
    0.14
    647
    0.14
    ivery
    0.14
    enses
    0.14
    Act Density 0.006%

    No Known Activations