INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     kulturn
    -0.09
    ロード
    -0.08
     Yankee
    -0.08
    stro
    -0.08
    Bound
    -0.08
    -0.08
    bidden
    -0.08
    (mid
    -0.08
    .Bounds
    -0.07
     فرهنگی
    -0.07
    POSITIVE LOGITS
     disable
    0.09
     automatically
    0.09
     génération
    0.08
     generation
    0.08
     marriage
    0.08
     génér
    0.08
     geração
    0.08
     тең
    0.08
     compress
    0.08
     essentials
    0.08
    Act Density 0.010%

    No Known Activations