INDEX
Explanations
instances of slashes in a document
New Auto-Interp
Negative Logits
L
-0.23
C
-0.22
S
-0.21
T
-0.20
F
-0.20
e
-0.20
y
-0.19
s
-0.19
*
-0.18
R
-0.18
POSITIVE LOGITS
scr
0.17
lot
0.17
tem
0.17
\/\/
0.16
tea
0.16
\\/
0.16
ies
0.16
rap
0.15
Ë
0.15
night
0.15
Activations Density 0.093%