INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    illin
    -0.06
     ebenfalls
    -0.06
    errated
    -0.06
     potential
    -0.06
     bom
    -0.06
    erequisites
    -0.06
     complicated
    -0.06
    emás
    -0.06
     iod
    -0.06
     знов
    -0.06
    POSITIVE LOGITS
    161
    0.07
     flap
    0.07
    ols
    0.06
     Greeks
    0.06
     Breitbart
    0.06
     DXGI
    0.06
    Česk
    0.06
     cấu
    0.06
     #[
    0.06
     Fusion
    0.06
    Act Density 0.001%

    No Known Activations