INDEX
    Explanations

    Events or spells

    New Auto-Interp
    Negative Logits
    CID
    -0.09
     Ե
    -0.08
    bys
    -0.08
     ove
    -0.08
    spread
    -0.08
     XLS
    -0.08
     երկ
    -0.08
    protected
    -0.08
     riots
    -0.08
    strijd
    -0.08
    POSITIVE LOGITS
    واض
    0.08
    包括
    0.08
     innovative
    0.08
     nakak
    0.08
    0.08
     иннова
    0.08
     innov
    0.08
     spanking
    0.07
    创新
    0.07
    aging
    0.07
    Act Density 0.001%

    No Known Activations