INDEX
Explanations
names of actors and their roles in movie descriptions
New Auto-Interp
Negative Logits
rist
-0.18
abby
-0.17
Sheldon
-0.15
ez
-0.15
005
-0.15
lop
-0.14
abi
-0.14
sdale
-0.14
504
-0.14
Gotham
-0.14
POSITIVE LOGITS
Threads
0.17
AGER
0.14
cast
0.14
agues
0.14
Bakan
0.14
Grü
0.14
(Thread
0.14
æĶ¿
0.13
-animate
0.13
ç¼
0.13
Activations Density 0.073%