INDEX
Explanations
lists of items and structure
New Auto-Interp
Negative Logits
eighty
0.58
sixty
0.55
seventy
0.54
nineteen
0.54
sixteen
0.53
fourteen
0.50
forty
0.50
seventeen
0.50
thirteen
0.48
Eighty
0.48
POSITIVE LOGITS
同樣
0.49
마찬가지
0.48
ibid
0.47
idem
0.46
unknown
0.46
столько
0.45
നിരവധി
0.45
countless
0.45
これも
0.45
indefinite
0.44
Activations Density 0.134%