INDEX
Explanations
references to video games and technology with a possible bias
phrases that express personal opinions or assessments
New Auto-Interp
Negative Logits
anwhile
-0.65
ornings
-0.58
eleph
-0.58
ãĤ©
-0.54
ipop
-0.54
helicop
-0.53
cliffe
-0.52
atson
-0.52
ogether
-0.51
iona
-0.51
POSITIVE LOGITS
Spoiler
0.65
Pokemon
0.63
OnePlus
0.62
GamerGate
0.62
ICO
0.61
feminism
0.59
Spoiler
0.59
sincere
0.59
atheists
0.58
Hearthstone
0.58
Activations Density 1.345%