INDEX
    Explanations

    war/violence

    New Auto-Interp
    Negative Logits
    ο
    -0.07
    umsuz
    -0.06
    /print
    -0.06
     جمله
    -0.06
    anoia
    -0.06
    -0.06
    он
    -0.06
    .scheduler
    -0.06
     addons
    -0.06
     مشکلات
    -0.06
    POSITIVE LOGITS
     kicked
    0.06
     Carson
    0.06
     marketer
    0.06
     welcome
    0.06
     poi
    0.06
     Eğitim
    0.06
     Attack
    0.06
    resse
    0.06
     specialize
    0.06
     Buyer
    0.06
    Act Density 0.052%

    No Known Activations