INDEX
Explanations
affirmative responses or expressions of agreement
New Auto-Interp
Negative Logits
ect
-0.19
andon
-0.15
Damn
-0.15
_VOID
-0.14
olley
-0.14
olle
-0.14
ãģįãģŁ
-0.14
Damn
-0.14
ine
-0.14
ão
-0.14
POSITIVE LOGITS
sure
0.24
yeah
0.23
sure
0.23
Yeah
0.19
yeah
0.18
Sure
0.18
Yeah
0.17
.GridView
0.16
hhh
0.16
redient
0.16
Activations Density 0.017%