INDEX
Explanations
famous historical figures and events
New Auto-Interp
Negative Logits
Occasionally
0.46
これまで
0.45
since
0.42
occasionally
0.42
Lately
0.42
Since
0.41
sejak
0.41
lately
0.40
ubiqu
0.40
지난
0.40
POSITIVE LOGITS
famously
1.02
famoso
0.88
famous
0.87
famosa
0.83
famosos
0.82
বিখ্যাত
0.80
berühm
0.79
знамени
0.78
据说
0.77
famed
0.74
Activations Density 0.016%