INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     kunnen
    -0.07
     overweight
    -0.07
     protoc
    -0.07
     bem
    -0.07
     scen
    -0.07
    uillet
    -0.07
     invoke
    -0.07
     Oklahoma
    -0.07
     landet
    -0.07
     ensure
    -0.07
    POSITIVE LOGITS
    Interval
    0.09
    Po
    0.09
    Che
    0.08
     Appearance
    0.08
    po
    0.08
     Po
    0.08
    Occurrences
    0.08
     religiosos
    0.08
    Appearance
    0.08
     Interval
    0.08
    Act Density 0.007%

    No Known Activations