INDEX
Explanations
proper names, particularly those of individuals, in various contexts
New Auto-Interp
Head Attr Weights
0:0.02
1:0.02
2:0.04
3:0.05
4:0.04
5:0.03
6:0.44
7:0.08
8:0.04
9:0.07
10:0.07
11:0.04
Negative Logits
incial
-1.67
Cosponsors
-1.60
urized
-1.44
yip
-1.36
psc
-1.33
heric
-1.32
ngth
-1.30
etsk
-1.28
iflower
-1.26
ormal
-1.24
POSITIVE LOGITS
schild
1.61
enegger
1.57
Duchess
1.41
cliffe
1.40
asca
1.35
Tsu
1.33
Bris
1.28
EStream
1.26
Tate
1.22
DonaldTrump
1.22
Activations Density 0.002%