INDEX
Explanations
imperative verbs or commands
New Auto-Interp
Head Attr Weights
0:0.10
1:0.07
2:0.08
3:0.06
4:0.07
5:0.08
6:0.10
7:0.10
8:0.08
9:0.08
10:0.07
11:0.07
Negative Logits
-2.36
efe
-2.11
urdue
-2.10
arma
-2.08
EStream
-2.05
LAPD
-2.02
Purdue
-1.98
chest
-1.97
required
-1.96
�
-1.95
POSITIVE LOGITS
mercial
2.23
graphs
2.20
queues
2.06
prominently
2.02
auctions
2.01
photographs
1.99
ads
1.94
photos
1.92
flags
1.91
loudspe
1.90
Activations Density 0.000%