INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    lerden
    -0.08
    napshot
    -0.08
     inok
    -0.08
     Hir
    -0.08
    ertal
    -0.08
    (command
    -0.07
    lardan
    -0.07
     preventiva
    -0.07
     licenses
    -0.07
     alust
    -0.07
    POSITIVE LOGITS
     Papa
    0.08
     grandma
    0.08
    uis
    0.08
     Florence
    0.08
     forced
    0.08
     Grandma
    0.08
     geprüft
    0.07
     Tribune
    0.07
    Obama
    0.07
     Joker
    0.07
    Act Density 0.001%

    No Known Activations