INDEX
Negative Logits
polygon
-0.10
polygon
-0.09
_polygon
-0.08
corpse
-0.08
angel
-0.08
annoying
-0.08
OWN
-0.08
architects
-0.08
arz
-0.08
policym
-0.07
POSITIVE LOGITS
assays
0.13
检测
0.12
assay
0.11
ಪರೀಕ್ಷ
0.10
detects
0.10
antibodies
0.10
परीक्षण
0.10
detecting
0.10
测试
0.10
detection
0.09
Activations Density 0.009%