INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ict
    -0.08
     które
    -0.07
    aar
    -0.06
     Image
    -0.06
     nama
    -0.06
     Maher
    -0.06
     cloak
    -0.06
    .review
    -0.06
    -0.06
     kontakte
    -0.06
    POSITIVE LOGITS
    spender
    0.08
    GW
    0.07
     فنی
    0.07
     bytesRead
    0.07
    grounds
    0.07
    _disp
    0.07
    0.07
     expenditures
    0.07
     expenditure
    0.07
    0.07
    Act Density 0.016%

    No Known Activations