INDEX
Explanations
the imperative form of actions
New Auto-Interp
Head Attr Weights
0:0.08
1:0.07
2:0.09
3:0.08
4:0.06
5:0.08
6:0.08
7:0.09
8:0.07
9:0.08
10:0.09
11:0.09
Negative Logits
izons
-2.23
Bind
-2.22
sonian
-2.19
ventional
-2.15
Thumbnail
-2.15
oto
-2.09
Experts
-2.00
Allen
-1.94
Ark
-1.90
itas
-1.90
POSITIVE LOGITS
throat
2.24
tyres
1.98
______
1.95
cant
1.93
stairs
1.91
throats
1.89
tunnels
1.88
loudspe
1.87
tyre
1.84
dressing
1.84
Activations Density 0.000%