INDEX
Explanations
references to totalitarianism and societal control
New Auto-Interp
Negative Logits
onet
-0.17
enheim
-0.16
vester
-0.15
abee
-0.14
iddi
-0.14
doch
-0.14
andel
-0.14
DateFormat
-0.14
Kapoor
-0.13
pleas
-0.13
POSITIVE LOGITS
arp
0.15
?url
0.15
/fonts
0.14
/buttons
0.13
ære
0.13
î
0.13
ald
0.13
_inventory
0.13
Kaplan
0.13
biology
0.12
Activations Density 0.070%