INDEX
Negative Logits
とな
-0.09
asured
-0.08
olivat
-0.08
идут
-0.08
dran
-0.08
cá
-0.08
_CLICK
-0.07
რაც
-0.07
čilo
-0.07
aanbieden
-0.07
POSITIVE LOGITS
subtle
0.08
Received
0.07
fi
0.07
plausible
0.07
Pear
0.07
neat
0.07
URG
0.07
footprint
0.07
automation
0.07
automatis
0.07
Activations Density 0.002%