INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    ubre
    -0.07
    нику
    -0.07
    (Screen
    -0.07
     Voll
    -0.07
    validator
    -0.06
     Finite
    -0.06
    -0.06
    ulario
    -0.06
    -0.06
     блю
    -0.06
    POSITIVE LOGITS
     oste
    0.10
    Operation
    0.07
     scaff
    0.06
     substitute
    0.06
     wor
    0.06
     Öz
    0.06
     northwest
    0.06
     heavens
    0.06
     infected
    0.06
     listening
    0.06
    Act Density 0.002%

    No Known Activations