INDEX
Explanations
mentions of facial recognition technology
New Auto-Interp
Negative Logits
izzo
-0.16
labeling
-0.15
Pager
-0.14
alarm
-0.14
ibri
-0.14
Wort
-0.13
оза
-0.13
çłĶ
-0.13
awan
-0.13
FIXME
-0.13
POSITIVE LOGITS
Aad
0.29
bi
0.26
Bi
0.22
cards
0.22
Cards
0.22
card
0.21
Bi
0.21
-card
0.20
Card
0.20
KY
0.20
Activations Density 0.017%