INDEX
Explanations
religious references and declarations from a divine figure
New Auto-Interp
Negative Logits
ulg
-0.18
ToLower
-0.15
ToUpper
-0.14
agal
-0.14
shan
-0.14
leer
-0.14
NgÃłnh
-0.14
pray
-0.13
ÅĦst
-0.13
ilee
-0.13
POSITIVE LOGITS
Lord
0.57
Lord
0.49
LORD
0.45
lord
0.42
Lords
0.31
lord
0.30
ÐĵоÑģп
0.26
lords
0.24
Father
0.24
Maker
0.24
Activations Density 0.165%