INDEX
Explanations
elements of critique related to film quality and character development
New Auto-Interp
Negative Logits
ê·¼
-0.15
angler
-0.14
祥
-0.14
_activity
-0.14
'gc
-0.14
activity
-0.14
Activity
-0.14
ymes
-0.14
mActivity
-0.14
agine
-0.14
POSITIVE LOGITS
overall
0.18
spoilers
0.18
Overall
0.17
spoon
0.16
background
0.16
overall
0.16
spoiled
0.16
Overall
0.16
spoil
0.15
Spo
0.15
Activations Density 0.036%