INDEX
Explanations
numerical values associated with studies or statistical data
New Auto-Interp
Negative Logits
uku
-0.14
oningen
-0.14
inka
-0.14
frank
-0.14
udden
-0.14
rank
-0.14
/kernel
-0.14
765
-0.13
sex
-0.13
assis
-0.13
POSITIVE LOGITS
opoulos
0.13
">//
0.13
isky
0.13
.INSTANCE
0.13
$__
0.13
#__
0.13
phia
0.13
eyin
0.13
reeze
0.12
steder
0.12
Activations Density 0.033%