INDEX
Explanations
No Explanations Found
New Auto-Interp
Head Attr Weights
0:0.08
1:0.08
2:0.07
3:0.08
4:0.07
5:0.08
6:0.07
7:0.09
8:0.08
9:0.08
10:0.08
11:0.09
Negative Logits
Whedon
-1.89
Ao
-1.81
Abrams
-1.76
eSports
-1.67
Bloody
-1.60
humor
-1.60
Catholicism
-1.60
laughs
-1.58
Gael
-1.54
paraph
-1.53
POSITIVE LOGITS
EVA
2.53
��
2.17
ividual
2.05
ressor
1.93
ridor
1.81
ⓘ
1.79
guiActiveUnfocused
1.78
llor
1.76
ネ
1.76
verning
1.74
Activations Density 0.000%
No Known Activations
This feature has no known activations.