INDEX
Explanations
metadata related to blog entries and publication information
New Auto-Interp
Head Attr Weights
0:0.18
1:0.02
2:0.07
3:0.13
4:0.07
5:0.14
6:0.04
7:0.10
8:0.07
9:0.02
10:0.09
11:0.02
Negative Logits
loudspe
-2.35
perf
-2.34
demonstrating
-2.22
witness
-2.11
viol
-2.06
recordings
-2.06
orchestr
-2.05
pian
-2.04
separately
-2.01
specification
-2.01
POSITIVE LOGITS
Canad
2.14
Gast
2.09
loo
2.06
Jet
2.06
atchewan
1.97
isure
1.94
Nova
1.93
ipeg
1.91
Leth
1.87
Winnipeg
1.85
Activations Density 0.001%