INDEX
Explanations
instances of interaction or dialogue among characters
New Auto-Interp
Negative Logits
475
-0.17
enÃŃ
-0.14
uhl
-0.14
dioxide
-0.14
KC
-0.14
497
-0.14
quia
-0.14
Gem
-0.14
Oasis
-0.14
tir
-0.14
POSITIVE LOGITS
oldown
0.16
ogui
0.15
erto
0.15
*)((
0.15
ertos
0.14
.datatables
0.14
ÅĻÃŃm
0.14
ÅĻen
0.14
ì¤
0.14
аж
0.14
Activations Density 0.024%