INDEX
Explanations
websites or URLs
URLs or web addresses
New Auto-Interp
Negative Logits
bark
-0.77
firing
-0.73
notch
-0.71
Emmy
-0.69
fired
-0.67
Kro
-0.66
Beir
-0.66
clin
-0.66
McCartney
-0.66
preferably
-0.66
POSITIVE LOGITS
forums
1.49
wp
1.49
cgi
1.48
articles
1.40
forum
1.35
archives
1.34
uploads
1.33
download
1.32
pmwiki
1.32
images
1.32
Activations Density 0.028%