INDEX
Explanations
restrictions related to photography and smoking in specific locations
New Auto-Interp
Negative Logits
avors
-0.16
oji
-0.15
Haut
-0.15
ole
-0.14
avar
-0.14
emin
-0.14
actionTypes
-0.14
ิร
-0.14
Physical
-0.13
diag
-0.13
POSITIVE LOGITS
Allowed
0.22
allowed
0.22
allowed
0.21
Allowed
0.21
permitted
0.20
forbidden
0.19
restricted
0.18
.rules
0.18
rules
0.17
å³°
0.17
Activations Density 0.101%