INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Rock
    -0.08
    orizontal
    -0.07
    OutOfRange
    -0.07
     rock
    -0.07
     نبود
    -0.06
     strcat
    -0.06
    _horizontal
    -0.06
    кат
    -0.06
     ape
    -0.06
    руч
    -0.06
    POSITIVE LOGITS
    _SE
    0.07
     теч
    0.07
    olutely
    0.06
     xảy
    0.06
    celand
    0.06
     Libyan
    0.06
     Wednesday
    0.06
    0.06
    oa
    0.06
    ensburg
    0.06
    Act Density 0.004%

    No Known Activations