INDEX
Explanations
punctuation and formatting elements in the text
New Auto-Interp
Negative Logits
esel
-0.16
rouw
-0.16
hardt
-0.16
ICO
-0.15
McCorm
-0.14
ipar
-0.14
zel
-0.14
autoload
-0.14
ett
-0.14
lop
-0.14
POSITIVE LOGITS
public
0.28
class
0.26
public
0.26
class
0.24
ami
0.19
import
0.18
class
0.17
public
0.17
veÅĻej
0.16
pública
0.16
Activations Density 0.009%