INDEX
Explanations
mentions of updates related to subscriptions or newsletters
New Auto-Interp
Head Attr Weights
0:0.01
1:0.01
2:0.09
3:0.13
4:0.04
5:0.07
6:0.21
7:0.10
8:0.04
9:0.06
10:0.07
11:0.12
Negative Logits
isSpecialOrderable
-1.40
tongues
-1.25
stakes
-1.24
mouths
-1.24
ovember
-1.21
pond
-1.17
bledon
-1.16
ebook
-1.16
Klux
-1.12
hurd
-1.12
POSITIVE LOGITS
occasional
1.39
scl
1.33
PH
1.29
APD
1.25
aints
1.24
ollower
1.23
rosso
1.23
Thumbnails
1.23
Additional
1.21
覚醒
1.17
Activations Density 0.001%