INDEX
Explanations
mentions of law enforcement accountability
instances of the word "the" in various contexts
New Auto-Interp
Negative Logits
fax
-0.83
nesty
-0.75
rade
-0.75
govtrack
-0.73
terness
-0.72
abuse
-0.72
because
-0.69
thereby
-0.69
voluntarily
-0.68
azel
-0.67
POSITIVE LOGITS
aforementioned
1.22
coolest
1.14
same
1.05
newest
1.04
hottest
1.03
latest
1.03
infamous
1.03
entirety
1.00
iconic
0.98
likes
0.97
Activations Density 0.907%