INDEX
Explanations
No Explanations Found
New Auto-Interp
Head Attr Weights
0:0.07
1:0.10
2:0.07
3:0.09
4:0.07
5:0.09
6:0.07
7:0.07
8:0.07
9:0.11
10:0.07
11:0.08
Negative Logits
grav
-1.58
itton
-1.57
predec
-1.57
nail
-1.56
Rowling
-1.50
Hut
-1.49
Kinnikuman
-1.49
Neander
-1.48
Boh
-1.48
grandchildren
-1.46
POSITIVE LOGITS
̶
2.03
broad
1.86
══
1.69
NAS
1.54
Spons
1.51
osate
1.50
anut
1.48
HTML
1.47
=~=~
1.47
Admin
1.46
Activations Density 0.000%
No Known Activations
This feature has no known activations.