INDEX
Explanations
references to mythical creatures or monsters
New Auto-Interp
Negative Logits
butterfly
-0.18
butterflies
-0.16
ecycle
-0.15
Marseille
-0.15
.Butter
-0.14
Butterfly
-0.14
unction
-0.14
968
-0.13
Ùħصر
-0.13
_REPLACE
-0.13
POSITIVE LOGITS
Sas
0.47
Big
0.38
Crypto
0.34
crypto
0.33
Crypto
0.32
Big
0.31
Crypt
0.31
crypt
0.28
crypto
0.28
crypt
0.26
Activations Density 0.021%