INDEX
Explanations
questions or statements posing questions
the phrase "the question" and its variations
New Auto-Interp
Negative Logits
rites
-0.89
ufact
-0.78
orpor
-0.77
emetery
-0.75
rylic
-0.71
é¾
-0.70
hiba
-0.69
luaj
-0.68
tsky
-0.66
âĹ¼
-0.65
POSITIVE LOGITS
naires
1.81
naire
1.53
posed
1.04
unanswered
1.00
answered
0.97
asked
0.92
mark
0.90
mark
0.89
questions
0.84
question
0.82
Activations Density 0.043%