INDEX
Explanations
phrases related to fictional characters or figures with the last name "Moriarty."
references to political parties
New Auto-Interp
Negative Logits
surpass
-0.69
prior
-0.65
designation
-0.63
listed
-0.63
Zeus
-0.61
monitoring
-0.61
measurement
-0.61
measures
-0.60
reduction
-0.58
previous
-0.58
POSITIVE LOGITS
arty
5.05
artisan
1.26
art
1.22
arts
1.21
arthy
1.16
elly
0.99
arter
0.99
ublic
0.98
ART
0.98
ahon
0.98
Activations Density 0.015%