INDEX
    Explanations

    specific U.S. states and countries

    New Auto-Interp
    Negative Logits
     ob
    -0.16
     Ob
    -0.16
    \Context
    -0.16
     hang
    -0.15
     ne
    -0.15
     hold
    -0.15
    -ob
    -0.15
     loose
    -0.15
     nom
    -0.15
     Bil
    -0.15
    POSITIVE LOGITS
    /Dk
    0.18
    acas
    0.17
     pornofilm
    0.16
    spÄĽ
    0.15
    iyon
    0.15
    iddet
    0.15
     pornost
    0.15
     pornofil
    0.15
     springfox
    0.15
    NSNotification
    0.14
    Act Density 0.055%

    No Known Activations