INDEX
Explanations
punctuation marks and their frequency in text
New Auto-Interp
Negative Logits
Pron
-0.17
synonymous
-0.15
property
-0.15
Spar
-0.15
Property
-0.14
ewn
-0.13
oon
-0.13
Pes
-0.13
Suff
-0.13
equation
-0.13
POSITIVE LOGITS
edom
0.17
hani
0.15
mite
0.15
_ABI
0.14
nl
0.14
tvb
0.14
надлеж
0.14
/stdc
0.14
SSIP
0.14
oleon
0.14
Activations Density 2.072%