INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     valore
    -0.07
    amaha
    -0.07
     follando
    -0.07
     neuken
    -0.07
     erfolgre
    -0.07
     выбира
    -0.07
     показ
    -0.06
    NewProp
    -0.06
     drop
    -0.06
    -0.06
    POSITIVE LOGITS
     intestinal
    0.13
    estinal
    0.10
     intestine
    0.10
     Prison
    0.08
     Skin
    0.07
     intest
    0.07
    	Il
    0.07
     Gardens
    0.07
     outside
    0.07
     Rect
    0.07
    Act Density 0.005%

    No Known Activations