INDEX
Explanations
instances of the word "go."
New Auto-Interp
Head Attr Weights
0:0.07
1:0.09
2:0.10
3:0.07
4:0.06
5:0.08
6:0.07
7:0.09
8:0.08
9:0.07
10:0.08
11:0.08
Negative Logits
princ
-2.26
AUTH
-2.22
respons
-2.13
recip
-2.07
taxp
-2.06
answ
-2.01
kins
-1.97
agos
-1.97
autos
-1.96
reet
-1.96
POSITIVE LOGITS
stuffing
2.22
Texture
2.21
Armored
2.14
Vapor
2.13
Stain
2.10
FORMATION
2.00
mallow
1.99
Vertical
1.95
Balls
1.95
Cum
1.92
Activations Density 0.000%