INDEX
Explanations
prepositions and phrases indicating relationships in time and space
New Auto-Interp
Negative Logits
Current
-0.18
CURRENT
-0.17
以åIJİ
-0.16
Currently
-0.16
currently
-0.16
CURRENT
-0.16
setattr
-0.16
_Current
-0.16
aktuellen
-0.16
current
-0.15
POSITIVE LOGITS
now
0.42
now
0.35
ahora
0.31
_now
0.31
-now
0.30
NOW
0.29
agora
0.28
Now
0.28
.now
0.28
اÙĦØ¢ÙĨ
0.28
Activations Density 0.073%