INDEX
Explanations
numerical references and statistics in academic papers
New Auto-Interp
Negative Logits
Alb
-0.15
segreg
-0.15
sey
-0.15
nal
-0.15
[
-0.15
cy
-0.15
versus
-0.14
inst
-0.14
ric
-0.14
micro
-0.14
POSITIVE LOGITS
ervo
0.20
ffset
0.16
ertime
0.16
ezier
0.15
argout
0.15
agy
0.15
αÏĥ
0.15
enza
0.15
caler
0.15
illian
0.15
Activations Density 0.032%