INDEX
Explanations
religious references or mentions
terms related to religion and its various implications
New Auto-Interp
Negative Logits
atable
-0.72
cleared
-0.63
mit
-0.62
golf
-0.61
client
-0.61
vel
-0.61
pad
-0.59
dump
-0.59
capsules
-0.59
daq
-0.59
POSITIVE LOGITS
Religion
3.39
Religious
1.74
Racial
1.03
igion
1.00
Belief
0.96
Divinity
0.89
Philosophy
0.88
urer
0.87
piety
0.87
School
0.87
Activations Density 0.023%