INDEX
Explanations
words related to physical body parts, specifically legs
occurrences of the word "leg."
New Auto-Interp
Negative Logits
aukee
-0.63
cffff
-0.62
tery
-0.62
vacancy
-0.62
Tycoon
-0.61
hower
-0.60
Moderate
-0.59
ongyang
-0.59
circumst
-0.59
Nare
-0.57
POSITIVE LOGITS
acies
1.11
iev
0.99
chair
0.88
locks
0.87
isl
0.85
leg
0.84
itimate
0.83
weed
0.80
ends
0.80
uct
0.79
Activations Density 0.008%