INDEX
Explanations
indications of significant change or transformation
New Auto-Interp
Head Attr Weights
0:0.12
1:0.10
2:0.11
3:0.07
4:0.09
5:0.09
6:0.10
7:0.03
8:0.07
9:0.05
10:0.05
11:0.06
Negative Logits
Telescope
-1.94
isSpecialOrderable
-1.65
GOODMAN
-1.62
HF
-1.53
JR
-1.45
[&
-1.44
GOT
-1.43
Takeru
-1.39
Played
-1.38
Watch
-1.38
POSITIVE LOGITS
�
1.58
ufficient
1.57
�
1.55
tta
1.54
pread
1.51
�
1.50
arty
1.49
¢
1.49
phy
1.49
ty
1.48
Activations Density 0.000%