INDEX
Negative Logits
Saved
-0.09
saved
-0.08
ergibt
-0.08
saved
-0.08
-saving
-0.08
Saved
-0.08
savings
-0.08
desperd
-0.08
ahorro
-0.08
去哪
-0.08
POSITIVE LOGITS
condem
0.10
sanctions
0.10
retali
0.10
condemnation
0.10
retaliation
0.09
withholding
0.09
condemn
0.09
issuance
0.09
hostility
0.09
rhetoric
0.09
Activations Density 0.039%