INDEX
    Explanations
    New Auto-Interp
    Negative Logits
    317
    -0.07
     LAT
    -0.07
    laden
    -0.07
    äter
    -0.07
    	current
    -0.06
    Returns
    -0.06
     currents
    -0.06
    657
    -0.06
    187
    -0.06
     trú
    -0.06
    POSITIVE LOGITS
     scope
    0.10
    Scope
    0.10
    cope
    0.09
     Scope
    0.09
    .Scope
    0.08
     scor
    0.08
     SCO
    0.08
     scoop
    0.08
     scop
    0.08
    (scope
    0.07
    Act Density 0.008%

    No Known Activations