INDEX
Explanations
various forms of engagement or connections in the text
New Auto-Interp
Negative Logits
erli
-0.17
oyer
-0.16
erno
-0.16
ix
-0.15
isma
-0.15
/
-0.14
ibold
-0.14
غة
-0.14
izr
-0.14
yh
-0.14
POSITIVE LOGITS
иÑĤом
0.16
_OID
0.15
AVIS
0.15
IRST
0.14
venge
0.14
ovky
0.14
ScrollBar
0.14
adel
0.14
preset
0.13
ektor
0.13
Activations Density 0.019%