INDEX
    Explanations

    mentions of sports teams and events

    New Auto-Interp
    Negative Logits
    ezvous
    -0.69
     brisk
    -0.67
    veyard
    -0.61
     Theft
    -0.58
    uncle
    -0.57
    ust
    -0.57
    escription
    -0.57
    illes
    -0.56
    astery
    -0.56
     delet
    -0.56
    POSITIVE LOGITS
     alike
    1.13
    erning
    0.93
     who
    0.87
    ãĤ®
    0.87
     wanting
    0.84
     wishing
    0.81
     downstream
    0.79
    umers
    0.79
     enthusi
    0.77
     aspiring
    0.76
    Act Density 1.956%

    No Known Activations