INDEX
Explanations
references to adaptations of literary works into films
New Auto-Interp
Negative Logits
ugin
-0.16
lint
-0.15
heit
-0.14
ingo
-0.14
undry
-0.14
orgot
-0.13
orpion
-0.13
át
-0.13
refin
-0.13
urette
-0.13
POSITIVE LOGITS
adapt
0.25
adapted
0.23
adapt
0.22
adaptation
0.21
adaptations
0.20
Adapt
0.19
source
0.19
based
0.18
adapting
0.18
source
0.17
Activations Density 0.179%