INDEX
Explanations
phrases related to processes of change or development
New Auto-Interp
Head Attr Weights
0:0.02
1:0.02
2:0.17
3:0.13
4:0.01
5:0.03
6:0.05
7:0.09
8:0.14
9:0.14
10:0.07
11:0.08
Negative Logits
ellow
-1.10
ielding
-1.05
aic
-1.04
onne
-1.03
zzy
-1.03
isSpecialOrderable
-1.02
anwhile
-1.01
_-
-1.00
quila
-1.00
oxin
-0.99
POSITIVE LOGITS
quest
1.20
amorph
1.11
fray
1.07
irc
1.05
locker
1.05
Coach
1.05
furt
1.02
plateau
1.02
士
1.01
>(
1.01
Activations Density 0.008%