INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.88
     Савезне
    -0.84
     mijne
    -0.81
    OGND
    -0.79
    ArgsConstructor
    -0.77
     occaf
    -0.77
    GEBURTS
    -0.75
     paille
    -0.75
     ainfi
    -0.75
     nahilalakip
    -0.74
    POSITIVE LOGITS
     goal
    0.57
     mission
    0.47
     pot
    0.44
     mix
    0.42
     body
    0.41
     agenda
    0.41
     objective
    0.40
     table
    0.40
     plan
    0.37
     good
    0.36
    Act Density 0.004%

    No Known Activations