INDEX
Explanations
references to television shows and their production details
New Auto-Interp
Head Attr Weights
0:0.05
1:0.11
2:0.02
3:0.03
4:0.02
5:0.43
6:0.02
7:0.01
8:0.03
9:0.10
10:0.08
11:0.03
Negative Logits
birds
-1.78
iasis
-1.73
thood
-1.55
bandits
-1.50
ukemia
-1.48
bia
-1.47
||||
-1.39
stru
-1.34
twins
-1.34
spir
-1.34
POSITIVE LOGITS
McMaster
1.81
displayText
1.58
Rosenstein
1.57
dated
1.47
lished
1.46
dating
1.42
QC
1.42
erred
1.42
lishing
1.39
GC
1.38
Activations Density 0.406%