INDEX
Explanations
strong emotional reactions to movies
New Auto-Interp
Negative Logits
erez
-0.15
definit
-0.14
Factory
-0.14
reuse
-0.14
@student
-0.13
basket
-0.13
Goals
-0.13
æ¥
-0.13
ponsor
-0.13
ÑĢаз
-0.13
POSITIVE LOGITS
kehr
0.15
ÙĤÙģ
0.15
.DOM
0.15
NodeType
0.14
Bracket
0.14
356
0.14
.camel
0.14
bara
0.13
Voll
0.13
TimeString
0.13
Activations Density 0.397%