INDEX
Explanations
topics related to weight loss and body fat reduction
New Auto-Interp
Negative Logits
Fragment
-0.16
ampo
-0.15
Heads
-0.15
alama
-0.15
fragment
-0.15
fragment
-0.15
ONGO
-0.15
Fucked
-0.14
lesia
-0.14
tpl
-0.14
POSITIVE LOGITS
fat
0.47
Fat
0.39
FAT
0.39
fat
0.37
-fat
0.35
adip
0.35
Fat
0.35
fats
0.31
èĦĤ
0.28
stubborn
0.26
Activations Density 0.068%