INDEX
Explanations
proper nouns and specific names related to individuals or groups
New Auto-Interp
Head Attr Weights
0:0.08
1:0.02
2:0.37
3:0.09
4:0.09
5:0.04
6:0.02
7:0.02
8:0.05
9:0.07
10:0.05
11:0.03
Negative Logits
captcha
-1.40
zoning
-1.28
itect
-1.22
suitable
-1.18
Siren
-1.18
vironment
-1.13
remotely
-1.11
config
-1.10
caucuses
-1.09
fif
-1.07
POSITIVE LOGITS
heit
1.63
anchester
1.37
ér
1.34
isco
1.28
ruary
1.25
Magn
1.24
Misty
1.21
aternity
1.19
itte
1.16
Wen
1.15
Activations Density 0.009%