INDEX
Explanations
words related to living organisms, particularly animals
New Auto-Interp
Head Attr Weights
0:0.04
1:0.05
2:0.07
3:0.27
4:0.03
5:0.03
6:0.13
7:0.08
8:0.05
9:0.05
10:0.07
11:0.09
Negative Logits
wcs
-1.72
ersed
-1.07
pport
-1.06
competitive
-1.05
orrow
-1.05
undermin
-1.03
occup
-1.01
Zeal
-1.01
summons
-1.00
xual
-0.99
POSITIVE LOGITS
endi
1.17
ETH
1.13
steen
1.12
Anat
1.08
Chao
1.06
Tile
1.04
Cth
1.03
reprint
1.01
sidx
1.00
龍�
1.00
Activations Density 0.002%