INDEX
Explanations
quotations and statements within quotation marks
New Auto-Interp
Negative Logits
Ross
-0.78
derby
-0.73
rall
-0.72
Creator
-0.70
Story
-0.70
affiliate
-0.69
Yam
-0.69
calendar
-0.69
Isaac
-0.69
rental
-0.68
POSITIVE LOGITS
absolutely
1.56
completely
1.48
very
1.47
almost
1.43
probably
1.43
extremely
1.42
significant
1.42
every
1.39
pretty
1.39
clear
1.38
Activations Density 0.316%