INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    olders
    -0.10
     Und
    -0.10
     und
    -0.08
    -0.08
    -0.08
     lifes
    -0.08
     springen
    -0.08
     infl
    -0.08
     Buildings
    -0.08
     Franchise
    -0.08
    POSITIVE LOGITS
    Affinity
    0.08
    Nevertheless
    0.08
    Population
    0.07
     sats
    0.07
    រ�
    0.07
    Character
    0.07
    0.07
    Err
    0.07
     ples
    0.07
    Gatt
    0.07
    Act Density 0.002%

    No Known Activations