INDEX
Explanations
temporal references related to timeframes in various contexts
New Auto-Interp
Head Attr Weights
0:0.04
1:0.02
2:0.20
3:0.13
4:0.04
5:0.03
6:0.20
7:0.07
8:0.05
9:0.04
10:0.08
11:0.06
Negative Logits
emis
-1.46
outheast
-1.36
uffer
-1.28
onto
-1.28
amera
-1.24
raper
-1.22
aeper
-1.22
utor
-1.20
eeds
-1.15
odder
-1.14
POSITIVE LOGITS
Corpus
1.34
Pulse
1.25
Sabb
1.19
Fraud
1.17
Portugal
1.16
Sass
1.16
Cas
1.15
Lans
1.14
Saban
1.13
Cosmos
1.13
Activations Density 0.010%