INDEX
Explanations
gerunds and related forms indicating duration or time
New Auto-Interp
Negative Logits
iom
-0.19
ector
-0.15
CELER
-0.15
cher
-0.15
Forge
-0.14
ëłĪìĬ¤
-0.14
uro
-0.14
itten
-0.14
iw
-0.13
aur
-0.13
POSITIVE LOGITS
chin
0.15
arsing
0.14
dane
0.14
fingerprint
0.14
kening
0.14
ulo
0.14
Jvm
0.13
дан
0.13
erna
0.13
Brow
0.13
Activations Density 0.002%