INDEX
Explanations
verbs related to pulling or tugging
words related to physical sensations and actions
New Auto-Interp
Negative Logits
ãĥ´
-0.71
Globe
-0.69
Dub
-0.69
Democr
-0.68
Panc
-0.66
Diary
-0.65
Countdown
-0.65
mberg
-0.65
itizens
-0.64
Fallen
-0.63
POSITIVE LOGITS
awed
0.95
levers
0.92
wrestle
0.88
eteenth
0.79
ument
0.79
ety
0.79
away
0.76
chairs
0.76
button
0.75
tug
0.74
Activations Density 0.072%