INDEX
Explanations
references to comedians and comedy-related content
New Auto-Interp
Negative Logits
εÏģγ
-0.18
vatel
-0.17
åĢĴ
-0.17
sustained
-0.15
اÛĮد
-0.14
Zot
-0.14
449
-0.14
oka
-0.14
antlr
-0.14
_encode
-0.14
POSITIVE LOGITS
Patton
0.23
Kum
0.23
Tig
0.21
Hann
0.20
Hasan
0.17
Natasha
0.17
paddle
0.17
ondo
0.16
Chelsea
0.16
Gilbert
0.15
Activations Density 0.014%