INDEX
Explanations
references to historical figures and events related to religious narratives
New Auto-Interp
Negative Logits
obl
-0.18
achi
-0.17
éné
-0.16
æİĽ
-0.15
IMIT
-0.15
lsru
-0.15
ordes
-0.15
è¼Ķ
-0.15
ãĥĪãĥª
-0.14
wpdb
-0.14
POSITIVE LOGITS
throw
0.15
throw
0.14
mer
0.14
Throw
0.14
gel
0.14
steller
0.14
Koch
0.13
ôn
0.13
horn
0.13
lander
0.13
Activations Density 0.040%