INDEX
Explanations
occurrences of the "/wp" token, indicating links related to WordPress content
New Auto-Interp
Negative Logits
æŀľ
-0.18
ual
-0.17
ymax
-0.16
Monk
-0.15
lier
-0.15
ude
-0.15
allah
-0.14
Appeals
-0.14
OUNDS
-0.14
ear
-0.14
POSITIVE LOGITS
ooled
0.18
712
0.16
uld
0.16
isky
0.15
ł
0.15
Nonce
0.15
rowad
0.14
Argb
0.14
conv
0.14
ìĭľìĺ¤
0.14
Activations Density 0.007%