INDEX
Explanations
time stamps or time indicators in a document
New Auto-Interp
Negative Logits
377
-0.23
376
-0.20
385
-0.18
387
-0.18
380
-0.18
397
-0.18
399
-0.17
336
-0.17
Miller
-0.17
391
-0.17
POSITIVE LOGITS
45
0.50
46
0.44
44
0.43
43
0.33
045
0.30
47
0.30
046
0.29
446
0.29
445
0.28
450
0.27
Activations Density 0.059%