INDEX
Explanations
surrounding or moving around
New Auto-Interp
Negative Logits
tfrac
0.37
leftmost
0.35
leftarrow
0.34
typeof
0.34
දහ
0.33
шкан
0.33
ótes
0.32
ύν
0.32
여기서
0.32
ことに
0.32
POSITIVE LOGITS
around
4.22
Around
3.86
around
3.84
вокруг
3.84
Around
3.83
autour
3.58
حول
3.53
alrededor
3.48
intorno
3.39
attorno
3.39
Activations Density 0.116%