INDEX
Explanations
time-related phrases and references
New Auto-Interp
Head Attr Weights
0:0.02
1:0.02
2:0.13
3:0.06
4:0.13
5:0.03
6:0.06
7:0.21
8:0.06
9:0.04
10:0.09
11:0.09
Negative Logits
luent
-1.44
apter
-1.43
aram
-1.36
terness
-1.30
ono
-1.28
alogue
-1.28
employed
-1.27
aldi
-1.26
ertodd
-1.26
anchester
-1.25
POSITIVE LOGITS
Emer
1.59
worms
1.58
Issue
1.35
Tend
1.32
iatus
1.25
August
1.25
anian
1.25
ILLE
1.24
ember
1.24
Nether
1.23
Activations Density 0.001%