INDEX
Explanations
numerical values and structural elements in text
New Auto-Interp
Negative Logits
av
-0.15
ivor
-0.14
off
-0.14
-off
-0.14
itat
-0.14
-offs
-0.14
flag
-0.13
gia
-0.13
FLAG
-0.13
Scho
-0.13
POSITIVE LOGITS
THON
0.15
AndUpdate
0.15
.apple
0.14
Ïģθ
0.14
Affero
0.14
istrovstvÃŃ
0.14
BuilderInterface
0.14
å½¢å¼ı
0.14
dök
0.13
upertino
0.13
Activations Density 0.103%