INDEX
Explanations
references to television channels and related programming content
New Auto-Interp
Head Attr Weights
0:0.03
1:0.05
2:0.09
3:0.21
4:0.02
5:0.02
6:0.13
7:0.12
8:0.04
9:0.11
10:0.06
11:0.07
Negative Logits
abase
-1.34
recoil
-1.17
utenberg
-1.17
stalk
-1.14
sip
-1.12
ometric
-1.11
nap
-1.06
enhagen
-1.06
bracket
-1.05
ktop
-1.05
POSITIVE LOGITS
archives
1.18
Office
1.14
ciating
1.12
accompan
1.12
Broadcasting
1.08
ibur
1.08
nown
1.08
washing
1.07
agents
1.07
Outer
1.07
Activations Density 0.007%