INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    naissance
    -0.07
     fixtures
    -0.07
    -0.06
     Seller
    -0.06
     Bottle
    -0.06
    Ul
    -0.06
    だから
    -0.06
    ColumnInfo
    -0.06
     factory
    -0.06
    ございます
    -0.06
    POSITIVE LOGITS
     شامل
    0.07
    сяг
    0.06
    _Check
    0.06
     sep
    0.06
    (samples
    0.06
    city
    0.06
    urred
    0.06
    suggest
    0.06
     Jesus
    0.06
    CHECK
    0.06
    Act Density 0.018%

    No Known Activations