INDEX
Explanations
references to the name "Bernard" and its variations
New Auto-Interp
Negative Logits
det
-0.16
rawer
-0.16
itech
-0.16
_CSR
-0.15
éric
-0.15
Filled
-0.15
ayd
-0.15
γε
-0.15
bie
-0.15
олоÑģ
-0.14
POSITIVE LOGITS
yz
0.18
ine
0.17
coni
0.16
psilon
0.16
Shaw
0.15
Gall
0.14
Odd
0.14
bro
0.14
bere
0.14
eger
0.14
Activations Density 0.012%