INDEX
Explanations
punctuation marks and their frequency in the text
New Auto-Interp
Negative Logits
rganization
-0.17
olume
-0.15
it
-0.15
s
-0.15
reen
-0.15
nt
-0.14
iec
-0.14
ÑĮ
-0.14
anes
-0.14
idges
-0.14
POSITIVE LOGITS
ottes
0.16
ạm
0.16
turned
0.16
ORG
0.15
esteem
0.15
ypse
0.14
illegal
0.14
ванов
0.14
зÑı
0.14
eks
0.14
Activations Density 0.672%