INDEX
Explanations
No Explanations Found
New Auto-Interp
Negative Logits
Gly
1.32
gly
1.21
Ge
1.20
Gr
1.20
Gly
1.13
gr
1.11
gly
1.11
wh
1.06
Rd
1.05
Bl
1.05
POSITIVE LOGITS
item
1.26
Item
1.23
ITEM
1.20
Item
1.13
ITEM
1.08
item
1.07
Kitten
1.01
barang
0.98
Items
0.94
barang
0.93
Activations Density 2.359%