INDEX
Explanations
references to spiritual or religious concepts involving good and evil
New Auto-Interp
Negative Logits
wie
-0.16
asco
-0.16
Dut
-0.16
Servers
-0.15
avo
-0.15
SEA
-0.15
mai
-0.15
ertino
-0.15
_VIRTUAL
-0.14
Ziel
-0.14
POSITIVE LOGITS
Religion
0.17
religion
0.17
Ant
0.15
Lyon
0.15
Sue
0.15
Mason
0.15
relig
0.15
Anti
0.15
itch
0.14
wax
0.14
Activations Density 0.011%