INDEX
Explanations
phrases related to distance or separation
instances of the word "dist" in various contexts
New Auto-Interp
Negative Logits
Falling
-0.68
swick
-0.67
scratch
-0.62
rehearsal
-0.61
downhill
-0.61
Benz
-0.61
falling
-0.61
briefs
-0.59
fall
-0.59
flashes
-0.59
POSITIVE LOGITS
anced
1.64
illation
1.63
ancing
1.51
illery
1.44
ributes
1.43
illing
1.35
iller
1.33
ributed
1.31
aste
1.30
ressing
1.29
Activations Density 0.038%