INDEX
Explanations
mentions of people and their roles or contributions in various contexts
New Auto-Interp
Negative Logits
Finished
-0.14
аÑĢи
-0.14
shal
-0.14
DÃŃky
-0.14
UPPORTED
-0.14
ynom
-0.14
εμÏĨ
-0.14
upported
-0.14
Supported
-0.14
ãģĵãĤį
-0.14
POSITIVE LOGITS
wanted
0.33
approached
0.29
wanted
0.29
sought
0.23
appro
0.23
decided
0.23
needed
0.22
knew
0.22
originally
0.21
initially
0.21
Activations Density 0.238%