INDEX
Explanations
No Explanations Found
New Auto-Interp
Negative Logits
enfans
-0.58
houſe
-0.53
cœurs
-0.47
neceff
-0.45
ftate
-0.39
larmes
-0.39
purpoſe
-0.38
ſtate
-0.38
perſon
-0.37
matchCondition
-0.36
POSITIVE LOGITS
/
0.97
/
0.73
../
0.65
}/
0.65
://
0.65
'/
0.64
../../
0.64
~/
0.64
../../../
0.63
/\.
0.62
Activations Density 0.000%
No Known Activations
This feature has no known activations.