INDEX
Explanations
language related to theological questions and societal impacts on beliefs
New Auto-Interp
Negative Logits
AZ
-0.18
AM
-0.18
Ap
-0.18
AV
-0.17
App
-0.17
ADM
-0.17
AD
-0.17
ADS
-0.16
ASS
-0.16
Ad
-0.15
POSITIVE LOGITS
aunt
0.31
asleep
0.29
afternoon
0.29
agony
0.29
avenues
0.29
awe
0.28
aroma
0.28
awake
0.28
audience
0.28
aerial
0.28
Activations Density 0.426%