INDEX
Explanations
uncertainty or doubt expressed in questioning statements
New Auto-Interp
Negative Logits
yor
-0.16
ropolis
-0.15
okane
-0.15
ÏİÏģα
-0.15
879
-0.14
нами
-0.14
ãĥ¬ãĥĥãĥĪ
-0.14
htdocs
-0.14
apes
-0.14
Kend
-0.14
POSITIVE LOGITS
nothing
0.25
çŃĶæ¡Ī
0.22
none
0.21
answer
0.21
nowhere
0.20
Answer
0.19
NONE
0.19
clue
0.19
None
0.18
Nothing
0.18
Activations Density 0.131%