INDEX
Explanations
phrase used in AI assistance
New Auto-Interp
Negative Logits
------
1.51
--------
1.49
-----
1.48
------------
1.46
-----------
1.46
-------
1.44
-------
1.42
…………
1.42
------
1.41
--------------
1.36
POSITIVE LOGITS
automl
0.78
rzeć
0.75
ต้า
0.74
Charlie
0.73
Tua
0.73
knię
0.72
Diff
0.71
Hundreds
0.70
悚
0.70
Gli
0.70
Activations Density 0.002%