INDEX
    Explanations

    Punctuation

    New Auto-Interp
    Negative Logits
     mimic
    -0.10
     imperson
    -0.09
    [int
    -0.09
     imitate
    -0.08
     voorzien
    -0.08
     Mim
    -0.08
    (Matrix
    -0.08
     Wohnungen
    -0.08
    [Test
    -0.08
     toilette
    -0.08
    POSITIVE LOGITS
    243
    0.08
    0.08
     Quil
    0.08
    šķ
    0.07
     Наз
    0.07
    Relacionado
    0.07
    you
    0.07
     Sout
    0.07
     quil
    0.07
    163
    0.07
    Act Density 0.001%

    No Known Activations