INDEX
Explanations
instances of the articles and conjunctions in the text
New Auto-Interp
Negative Logits
j
-0.16
lund
-0.15
bble
-0.15
u
-0.15
avier
-0.15
nap
-0.15
VERR
-0.15
ald
-0.15
itage
-0.15
rud
-0.14
POSITIVE LOGITS
través
0.21
partir
0.18
odom
0.18
credit
0.16
моÑĢ
0.16
aÄį
0.16
hus
0.16
ÐŁÐŀ
0.15
rios
0.15
equal
0.15
Activations Density 0.014%