INDEX
Explanations
connections to community events and facilities
New Auto-Interp
Negative Logits
поба
-0.15
_Internal
-0.14
Hindered
-0.14
_faces
-0.14
ÑģкладÑĥ
-0.13
.Listener
-0.13
#af
-0.13
zk
-0.13
entine
-0.13
gebn
-0.13
POSITIVE LOGITS
serving
0.24
figures
0.24
figure
0.22
housing
0.20
catering
0.20
supplying
0.20
providing
0.20
filled
0.19
hosting
0.19
figures
0.18
Activations Density 0.034%