INDEX
Explanations
tables summarizing differences
New Auto-Interp
Negative Logits
our
0.71
نزدیک
0.67
closer
0.67
during
0.66
OUR
0.66
history
0.65
History
0.63
Our
0.62
history
0.62
before
0.60
POSITIVE LOGITS
persoane
0.84
0.81
🥰
0.81
Kleid
0.81
------------
0.80
✅
0.79
तुम्ही
0.79
alguien
0.79
segni
0.79
leche
0.79
Activations Density 0.085%