INDEX
Negative Logits
ABCDE
-0.09
spot
-0.09
precisamos
-0.08
퍼
-0.08
(pos
-0.08
锐
-0.08
SEMB
-0.08
unseres
-0.08
Spot
-0.08
leck
-0.08
POSITIVE LOGITS
Wiki
0.09
Wikipedia
0.09
wiki
0.09
wiki
0.09
wikipedia
0.08
]]
0.08
0.08
]].
0.08
controversies
0.07
recreational
0.07
Activations Density 0.024%