INDEX
Explanations
instances of the word "except" and its variations
New Auto-Interp
Negative Logits
isman
-0.17
pone
-0.16
inkel
-0.16
lái
-0.15
Ñĥнк
-0.15
xon
-0.15
xiv
-0.15
Symfony
-0.14
inati
-0.14
oste
-0.14
POSITIVE LOGITS
ing
0.25
acular
0.18
io
0.16
ting
0.16
ta
0.16
ive
0.15
ech
0.15
tion
0.15
sa
0.14
elden
0.14
Activations Density 0.026%