INDEX
Explanations
references to the word "turmeric" and its variations
New Auto-Interp
Negative Logits
ê·ł
-0.18
apus
-0.17
oggler
-0.16
urge
-0.16
lad
-0.15
Rays
-0.15
stown
-0.15
lle
-0.14
.inline
-0.14
orners
-0.14
POSITIVE LOGITS
tur
0.26
Tur
0.26
meric
0.24
tur
0.20
Tur
0.20
keys
0.20
kish
0.20
quoise
0.19
Tuy
0.18
turb
0.17
Activations Density 0.012%