INDEX
Explanations
references to prestigious events and awards in the film and documentary industry
New Auto-Interp
Negative Logits
new
-0.16
nn
-0.15
2
-0.14
ities
-0.14
ony
-0.14
new
-0.14
ab
-0.14
acio
-0.14
bu
-0.14
4
-0.14
POSITIVE LOGITS
.scalablytyped
0.21
endregion
0.16
geist
0.16
yılda
0.15
ekim
0.15
TOTYPE
0.15
Snippet
0.15
Unmarshaller
0.15
ydk
0.15
steder
0.15
Activations Density 0.063%