INDEX
Explanations
mention of facial recognition technology and related systems
New Auto-Interp
Negative Logits
holm
-0.16
raf
-0.16
ahlen
-0.15
XF
-0.15
olo
-0.14
sponsor
-0.14
avana
-0.14
Hamas
-0.14
UTC
-0.13
erah
-0.13
POSITIVE LOGITS
ynamo
0.18
asthan
0.17
ẫn
0.16
Math
0.15
834
0.14
cont
0.14
ynos
0.14
Gow
0.14
bsub
0.14
pray
0.14
Activations Density 1.255%