INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     zoekt
    -0.08
    Ant
    -0.08
     esper
    -0.08
    antar
    -0.08
     Raf
    -0.07
     تاکید
    -0.07
     ngủ
    -0.07
    -0.07
     Karena
    -0.07
    Lin
    -0.07
    POSITIVE LOGITS
     pneumatic
    0.09
     bard
    0.08
     сот
    0.07
    0.07
     pyn
    0.07
     Pne
    0.07
    ура
    0.07
     ramifications
    0.07
     depletion
    0.07
     ни
    0.07
    Act Density 0.052%

    No Known Activations