INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Gers
    -0.08
    Turkey
    -0.08
     Mature
    -0.08
     cosa
    -0.08
    -0.08
    _cart
    -0.07
     Cui
    -0.07
    arras
    -0.07
    ču
    -0.07
    -0.07
    POSITIVE LOGITS
     مِن
    0.08
     εμπ
    0.08
     infe
    0.07
    වා
    0.07
     inférieur
    0.07
     devis
    0.07
    ðu
    0.07
     painless
    0.07
     tale
    0.07
     Stanton
    0.07
    Act Density 0.163%

    No Known Activations