INDEX
Explanations
text related to official government entities or departments
references to governmental and organizational entities
New Auto-Interp
Negative Logits
bleed
-0.80
lins
-0.72
voic
-0.68
jerk
-0.67
len
-0.66
juicy
-0.66
unpredict
-0.65
spoilers
-0.65
hitch
-0.65
uphill
-0.65
POSITIVE LOGITS
arthed
0.90
Colleges
0.87
Directorate
0.86
headquartered
0.83
ĸļ
0.80
Campus
0.76
Faculty
0.75
chaired
0.74
FontSize
0.74
Division
0.73
Activations Density 0.716%