INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    екті
    -0.08
     inj
    -0.08
     escorted
    -0.08
    UST
    -0.08
    .Back
    -0.07
     barrels
    -0.07
    ौती
    -0.07
    INS
    -0.07
     الأس
    -0.07
     Uri
    -0.07
    POSITIVE LOGITS
     grazie
    0.10
     gracias
    0.09
    0.08
     zahval
    0.08
     díky
    0.08
    ibility
    0.08
     dankzij
    0.08
     благодаря
    0.08
     grâce
    0.08
    .receive
    0.08
    Act Density 0.011%

    No Known Activations