INDEX
Explanations
historical references related to church figures and events
New Auto-Interp
Negative Logits
BackingField
-0.14
δο
-0.14
à¸ĺาà¸Ļ
-0.14
daq
-0.13
æĶ
-0.13
Animalia
-0.13
ãĥ¼ãĥį
-0.13
neod
-0.13
dete
-0.13
ë²Ī
-0.13
POSITIVE LOGITS
mon
0.49
monastery
0.46
monks
0.43
monk
0.39
abb
0.37
clo
0.36
Benedict
0.34
-mon
0.34
mon
0.33
Mon
0.32
Activations Density 0.120%