INDEX
Explanations
the word "pull" used in various contexts
phrases related to the action of pulling
New Auto-Interp
Negative Logits
ibel
-0.73
merce
-0.72
nown
-0.68
chance
-0.68
ldom
-0.67
llor
-0.66
cius
-0.65
ILCS
-0.65
icol
-0.64
lain
-0.64
POSITIVE LOGITS
levers
1.05
punches
0.92
aggro
0.90
away
0.84
weeds
0.84
pull
0.82
off
0.82
strings
0.81
awa
0.80
out
0.79
Activations Density 0.034%