INDEX
Explanations
tokens that refer to quantities or counts, particularly relating to numbers and their representations
New Auto-Interp
Negative Logits
насељу
-0.94
kater
-0.69
CrossRef
-0.67
titian
-0.63
〗
-0.62
dır
-0.61
ScopeManager
-0.59
Datuak
-0.59
↓↓
-0.59
featureID
-0.58
POSITIVE LOGITS
One
1.19
One
1.18
Oneida
1.03
ONE
1.03
ONE
1.03
OneNote
0.96
Ones
0.92
hundred
0.91
one
0.90
ワン
0.89
Activations Density 0.134%