INDEX
Explanations
phrases that involve requests or desires for something
New Auto-Interp
Negative Logits
mand
-0.15
oria
-0.15
yen
-0.15
orio
-0.14
bbing
-0.14
osto
-0.14
à¥ĩà¤Łà¤°
-0.14
оген
-0.14
DIC
-0.14
247
-0.14
POSITIVE LOGITS
akin
0.15
},{↵0.15
ki
0.14
å±ħ
0.14
Pruitt
0.14
Ordinal
0.13
_HEADERS
0.13
mall
0.13
è´
0.13
íķ´
0.13
Activations Density 0.067%