INDEX
Explanations
proper nouns related to a specific person named Marc
occurrences of the name "Marc."
New Auto-Interp
Negative Logits
itness
-0.79
FUL
-0.78
OTE
-0.77
velt
-0.74
milo
-0.72
irlf
-0.71
LLOW
-0.71
worldly
-0.68
SUP
-0.66
SEAL
-0.65
POSITIVE LOGITS
ouf
0.93
afort
0.93
agne
0.93
ques
0.86
anson
0.84
otti
0.84
anton
0.83
Marc
0.83
ia
0.82
angelo
0.82
Activations Density 0.017%