INDEX
Explanations
references to religious figures and their testimonies
New Auto-Interp
Negative Logits
ãĥ¼ãĥ
-0.18
æĺĩ
-0.16
.gwt
-0.15
ialis
-0.15
_reporting
-0.15
orny
-0.15
име
-0.15
ÙħÙĤ
-0.14
decorate
-0.14
_ABI
-0.14
POSITIVE LOGITS
mal
0.25
Mal
0.25
Mal
0.23
MAL
0.20
mal
0.17
malt
0.17
æĬ
0.16
Malk
0.16
MAL
0.16
pall
0.16
Activations Density 0.035%