INDEX
Explanations
mentions of the name "Santos"
New Auto-Interp
Negative Logits
emann
-0.16
ones
-0.16
aptured
-0.15
Schn
-0.15
ought
-0.14
emin
-0.14
.scheme
-0.14
usal
-0.14
zym
-0.14
CDATA
-0.14
POSITIVE LOGITS
ires
0.16
θι
0.15
okie
0.15
-navigation
0.14
isher
0.14
rium
0.14
ookie
0.14
pson
0.13
ok
0.13
aden
0.13
Activations Density 0.003%