INDEX
Explanations
terms related to preaching or religious discourse
New Auto-Interp
Negative Logits
Samara
-0.61
Tivoli
-0.60
ILS
-0.59
Param
-0.57
IDF
-0.56
Lotte
-0.54
Sully
-0.54
TAWA
-0.54
Gina
-0.53
Argon
-0.53
POSITIVE LOGITS
preach
1.55
preaching
1.45
preached
1.45
preachers
1.13
preacher
1.11
Preacher
0.95
TAMBÉM
0.67
Referencie
0.59
peindre
0.58
пропо
0.54
Activations Density 0.003%