INDEX
Explanations
punctuations and formatting symbols used in written language
New Auto-Interp
Negative Logits
ssp
-0.16
tir
-0.15
nesc
-0.15
blr
-0.14
uido
-0.14
Laboratories
-0.14
ollar
-0.14
uida
-0.14
stab
-0.13
öy
-0.13
POSITIVE LOGITS
Born
0.19
Bio
0.19
Born
0.19
bio
0.18
Mr
0.17
born
0.17
bio
0.17
Bio
0.17
Prior
0.16
BIO
0.15
Activations Density 0.046%