INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     Amen
    -0.08
     Pest
    -0.08
     Karen
    -0.08
    ολ
    -0.07
     Wein
    -0.07
     Karl
    -0.07
     Ernest
    -0.07
    sap
    -0.07
    uron
    -0.07
     Thur
    -0.07
    POSITIVE LOGITS
     scars
    0.11
    .Inner
    0.10
     scratches
    0.09
     wounds
    0.08
     scratched
    0.08
    co
    0.08
     blem
    0.08
     tattoos
    0.08
    boards
    0.08
     caused
    0.08
    Act Density 0.005%

    No Known Activations