INDEX
Explanations
references to the name "Wayne" and related variations
New Auto-Interp
Negative Logits
osen
-0.17
auss
-0.16
abi
-0.14
¶Į
-0.14
olph
-0.14
Stall
-0.14
Scal
-0.14
stall
-0.14
rlen
-0.14
labs
-0.14
POSITIVE LOGITS
Dixon
0.15
efs
0.15
.awt
0.14
WD
0.14
æī£
0.14
widow
0.13
_nsec
0.13
zn
0.13
none
0.13
awah
0.13
Activations Density 0.002%