INDEX
Explanations
references to "secular" concepts and terms related to secularism
New Auto-Interp
Negative Logits
ymoon
-0.16
akk
-0.16
å¾ģ
-0.15
ysa
-0.15
croft
-0.15
cene
-0.15
utz
-0.15
idy
-0.15
è¾°
-0.14
ÃŃv
-0.14
POSITIVE LOGITS
urities
0.24
URITY
0.21
und
0.21
ession
0.20
uring
0.19
oundary
0.18
uencia
0.18
ularity
0.18
ular
0.18
ateurs
0.17
Activations Density 0.011%