INDEX
Explanations
references to physical running or motion
instances of the word "run" in various contexts
New Auto-Interp
Negative Logits
Virtue
-0.63
Hots
-0.62
Birth
-0.60
isively
-0.59
olia
-0.59
Pick
-0.57
Males
-0.57
Aires
-0.57
Revolution
-0.54
Mai
-0.53
POSITIVE LOGITS
swick
1.25
aways
1.25
gs
1.19
escape
1.19
nings
1.17
ners
1.06
ways
1.05
nels
1.02
away
1.00
bys
1.00
Activations Density 0.039%