INDEX
Explanations
past and future time references
New Auto-Interp
Negative Logits
Lim
0.80
اولین
0.79
பெரும்பாலும்
0.76
Unlimited
0.76
انتہائی
0.76
Equally
0.76
erstmal
0.74
zweimal
0.72
وی
0.72
毎回
0.71
POSITIVE LOGITS
ago
1.58
shy
1.41
before
1.19
later
1.13
apart
1.13
ahead
1.10
removed
1.07
past
1.03
earlier
1.02
behind
0.98
Activations Density 0.129%