INDEX
Negative Logits
throat
-0.09
inco
-0.08
photos
-0.08
chle
-0.08
immersion
-0.08
ِي
-0.08
Wagon
-0.08
heli
-0.07
Rubin
-0.07
Gregorian
-0.07
POSITIVE LOGITS
(ip
0.10
physics
0.10
idol
0.09
_ip
0.09
част
0.09
ip
0.09
physics
0.08
Dean
0.08
.IP
0.08
Physics
0.08
Activations Density 0.117%