INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     textbook
    -0.09
    -0.08
     divine
    -0.08
     lịch
    -0.08
     presentamos
    -0.08
     shedding
    -0.07
     tenemos
    -0.07
     bomen
    -0.07
     teor
    -0.07
     Norð
    -0.07
    POSITIVE LOGITS
    <ID
    0.08
    ophobic
    0.08
    udo
    0.08
    Ime
    0.08
     Tasche
    0.08
    (child
    0.08
    ueden
    0.08
    .UTF
    0.07
    ,使
    0.07
     imperme
    0.07
    Act Density 0.003%

    No Known Activations