INDEX
Explanations
mentions of the name "Gib" or variations of it
New Auto-Interp
Negative Logits
uction
-0.17
ifice
-0.16
atro
-0.15
lea
-0.15
lagen
-0.15
_stamp
-0.15
ynes
-0.14
yle
-0.14
ifique
-0.14
ific
-0.14
POSITIVE LOGITS
bons
0.36
bs
0.24
bon
0.24
bsite
0.23
aldi
0.23
eah
0.21
sons
0.20
bz
0.20
ney
0.19
ber
0.19
Activations Density 0.004%