INDEX
Explanations
common conjunctions and auxiliary verbs used in context
New Auto-Interp
Negative Logits
ijľ
-0.16
anz
-0.15
bil
-0.15
etter
-0.14
cao
-0.14
divers
-0.14
Meg
-0.14
-ser
-0.13
æŁĵ
-0.13
bik
-0.13
POSITIVE LOGITS
azzi
0.20
prior
0.20
_prior
0.16
gold
0.15
prior
0.15
omo
0.15
ãĤĩ
0.15
Prior
0.14
ancel
0.14
iesel
0.14
Activations Density 0.000%