INDEX
Explanations
verbs or expressions related to movement away from something
instances of the word "away" in various contexts
New Auto-Interp
Negative Logits
ammy
-0.80
oly
-0.80
milo
-0.74
elly
-0.72
immer
-0.69
annis
-0.68
ummer
-0.68
ionic
-0.67
xual
-0.66
ingham
-0.66
POSITIVE LOGITS
RAY
0.71
away
0.70
à©
0.69
doors
0.67
away
0.66
ı
0.66
oslav
0.65
OOD
0.65
ï¸
0.65
FROM
0.64
Activations Density 0.028%