INDEX
Explanations
concepts related to belief systems and religion
New Auto-Interp
Negative Logits
̧
-0.16
achs
-0.16
jist
-0.14
lish
-0.14
niÄį
-0.14
CAS
-0.13
ziej
-0.13
浪
-0.13
Exceptions
-0.13
ç¡
-0.13
POSITIVE LOGITS
religion
0.37
belief
0.35
religions
0.30
mono
0.30
Religion
0.30
beliefs
0.28
belief
0.26
Mono
0.25
rel
0.23
religious
0.23
Activations Density 0.226%