INDEX
Explanations
phrases related to leaving or staying in a certain place or situation
New Auto-Interp
Head Attr Weights
0:0.06
1:0.01
2:0.26
3:0.05
4:0.10
5:0.05
6:0.02
7:0.01
8:0.26
9:0.07
10:0.04
11:0.01
Negative Logits
MN
-1.57
Cosponsors
-1.44
Plugin
-1.36
SHIP
-1.34
ALLY
-1.26
GW
-1.26
arella
-1.25
igree
-1.25
rss
-1.22
aldi
-1.22
POSITIVE LOGITS
azeera
1.45
voic
1.41
footprints
1.35
ashes
1.30
premises
1.30
undone
1.29
crater
1.28
rette
1.28
unfinished
1.27
restraints
1.24
Activations Density 0.040%