INDEX
Explanations
official communications and statements related to events or incidents
New Auto-Interp
Negative Logits
γά
-0.18
659
-0.17
ëłµ
-0.16
auf
-0.15
cri
-0.15
ause
-0.14
ÙĪÙĦÙĪØ¬
-0.14
ellar
-0.14
ayet
-0.14
hear
-0.14
POSITIVE LOGITS
saying
0.30
about
0.23
stating
0.20
regarding
0.20
concerning
0.19
pur
0.18
addressed
0.17
promising
0.17
about
0.17
vá»ģ
0.17
Activations Density 0.214%