INDEX
Explanations
URLs or email addresses
URLs and email addresses
New Auto-Interp
Negative Logits
Maher
-0.86
Rye
-0.79
Jihad
-0.78
tabloid
-0.77
refrain
-0.76
Krugman
-0.75
tongue
-0.75
sequence
-0.74
bitterness
-0.73
tease
-0.72
POSITIVE LOGITS
english
1.41
1.40
events
1.30
cit
1.28
gp
1.24
www
1.23
global
1.22
south
1.19
john
1.18
gmail
1.17
Activations Density 0.093%