INDEX
Explanations
instances of interpersonal relationships and interactions among characters
New Auto-Interp
Negative Logits
ven
-0.15
v
-0.15
rikes
-0.15
iek
-0.15
zb
-0.14
ocha
-0.14
324
-0.14
Couple
-0.14
ANGER
-0.14
еÑĤÑĭ
-0.14
POSITIVE LOGITS
кÑĢа
0.18
radu
0.17
@nate
0.16
.localized
0.16
iaux
0.15
Edwards
0.15
Dyn
0.15
Bloc
0.14
élé
0.14
eron
0.14
Activations Density 0.335%