INDEX
Explanations
instances of parentheses and related structures in the text
New Auto-Interp
Negative Logits
adr
-0.17
_DDR
-0.16
DDL
-0.16
лада
-0.15
cotton
-0.15
adar
-0.15
ccp
-0.14
Cotton
-0.13
.cc
-0.13
691
-0.13
POSITIVE LOGITS
MMC
0.30
SRC
0.30
ERC
0.28
CRC
0.28
WSC
0.28
AAC
0.27
CRC
0.27
MSC
0.27
IPC
0.27
ERC
0.27
Activations Density 0.017%