INDEX
Explanations
terms related to the immune system
New Auto-Interp
Negative Logits
kt
-0.17
afa
-0.17
olson
-0.16
dot
-0.16
deg
-0.15
avl
-0.15
reet
-0.15
rew
-0.14
kir
-0.14
xi
-0.14
POSITIVE LOGITS
system
0.30
-system
0.24
System
0.24
system
0.24
/auto
0.23
System
0.20
ystem
0.20
_system
0.20
ç³»ç»Ł
0.20
_System
0.20
Activations Density 0.010%