INDEX
    Explanations

    mixed content/languages

    New Auto-Interp
    Negative Logits
    .Member
    -0.07
    .Act
    -0.07
    .Set
    -0.07
     Failed
    -0.07
     MOL
    -0.07
     Alien
    -0.07
     parlament
    -0.07
    .Password
    -0.07
     Fans
    -0.07
     Manager
    -0.07
    POSITIVE LOGITS
    ensp
    0.09
    ensen
    0.09
    both
    0.08
     bah
    0.08
    bah
    0.08
    Ба
    0.08
    enj
    0.08
    drink
    0.08
     róż
    0.08
    bas
    0.08
    Act Density 0.000%

    No Known Activations