INDEX
Explanations
actions related to moving or transitioning from one state or place to another
New Auto-Interp
Negative Logits
ewed
-0.15
olan
-0.15
ewing
-0.15
FromFile
-0.14
roj
-0.14
amas
-0.14
itat
-0.14
Opport
-0.14
éĮ
-0.14
dev
-0.13
POSITIVE LOGITS
went
0.18
packing
0.17
into
0.17
broke
0.17
bankrupt
0.17
home
0.16
somewhere
0.16
went
0.16
abroad
0.15
away
0.15
Activations Density 0.059%