INDEX
Explanations
terms related to environmental impact and sustainability
New Auto-Interp
Negative Logits
oro
-0.16
Weinstein
-0.16
din
-0.15
din
-0.15
Ha
-0.15
aro
-0.15
Din
-0.14
ird
-0.14
adin
-0.14
ovi
-0.14
POSITIVE LOGITS
enido
0.17
annels
0.17
anou
0.16
iffies
0.15
uforia
0.15
saida
0.15
ANNEL
0.14
persona
0.14
Ïĥε
0.14
aÅŁÄ±
0.14
Activations Density 0.130%