INDEX
Explanations
mentions of the term "Dot"
references to the game "DotA."
New Auto-Interp
Negative Logits
uberty
-0.81
eele
-0.69
éĹĺ
-0.67
IENCE
-0.65
aired
-0.65
utherford
-0.64
perm
-0.63
ocene
-0.62
iscopal
-0.62
icago
-0.62
POSITIVE LOGITS
Dot
1.06
zeb
0.99
dot
0.98
lings
0.75
rice
0.74
izens
0.74
Designs
0.73
zh
0.72
yond
0.71
amphetamine
0.69
Activations Density 0.006%