INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     twor
    -0.08
    -0.08
     piezas
    -0.08
    одар
    -0.08
     domingos
    -0.08
     documental
    -0.08
     trung
    -0.08
     domingo
    -0.08
     USB
    -0.07
     lait
    -0.07
    POSITIVE LOGITS
     collapse
    0.09
     beoordelen
    0.08
     έν
    0.08
     collapsed
    0.08
     collapsing
    0.08
     prune
    0.08
    .city
    0.08
     beoordeling
    0.07
     શહેર
    0.07
     City
    0.07
    Act Density 0.003%

    No Known Activations