INDEX
Explanations
proper nouns and names
names of people or places
New Auto-Interp
Head Attr Weights
0:0.05
1:0.04
2:0.21
3:0.06
4:0.12
5:0.10
6:0.03
7:0.03
8:0.05
9:0.18
10:0.05
11:0.03
Negative Logits
skelet
-1.63
brig
-1.36
smoked
-1.35
cooked
-1.23
Rove
-1.23
psychiat
-1.19
steroid
-1.16
gamb
-1.16
rehabilit
-1.15
dynam
-1.14
POSITIVE LOGITS
fecture
1.70
riks
1.60
boa
1.51
kai
1.49
ensis
1.45
anca
1.43
vu
1.42
ère
1.39
�
1.36
arta
1.36
Activations Density 0.002%