INDEX
Explanations
chronological references and key names in an academic context
New Auto-Interp
Negative Logits
Mall
-0.17
/modules
-0.17
uman
-0.17
Manson
-0.16
Maiden
-0.16
Mund
-0.16
Mansion
-0.15
mund
-0.15
κοÏĤ
-0.15
Modular
-0.15
POSITIVE LOGITS
mic
1.24
Mic
1.14
MIC
1.13
MIC
1.06
mic
1.05
Mic
1.02
Mike
0.98
Michael
0.98
mike
0.97
mik
0.96
Activations Density 0.313%