INDEX
Explanations
parentheses and statements related to membership or inclusion in organizations
New Auto-Interp
Negative Logits
ac
-0.18
adr
-0.16
.cc
-0.16
ac
-0.15
ec
-0.15
uc
-0.15
sc
-0.14
adar
-0.14
лада
-0.14
ccp
-0.14
POSITIVE LOGITS
MMC
0.30
PMC
0.30
IPC
0.29
SRC
0.29
ERC
0.28
WSC
0.27
PMC
0.27
RTC
0.26
RPC
0.26
MPC
0.25
Activations Density 0.014%