INDEX
Explanations
names related to people
proper nouns, specifically names of individuals and brands associated with them
New Auto-Interp
Head Attr Weights
0:0.09
1:0.02
2:0.29
3:0.07
4:0.17
5:0.05
6:0.02
7:0.02
8:0.07
9:0.08
10:0.05
11:0.02
Negative Logits
Fukushima
-1.21
contrace
-1.18
exchanges
-1.18
recomb
-1.14
outp
-1.10
overload
-1.09
pend
-1.05
blogs
-1.05
VIDEOS
-1.05
fluoride
-1.05
POSITIVE LOGITS
idy
1.44
oola
1.42
reau
1.35
gey
1.33
ç
1.29
idas
1.26
ère
1.26
ieri
1.25
uda
1.23
Tile
1.22
Activations Density 0.004%