INDEX

Explanations

known for positive attributes

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Para

0.49

Para

0.49

 para

0.44

para

0.44

 PARA

0.41

validacion

0.39

 Tube

0.37

适用于

0.37

 Nuclear

0.37

 dominant

0.37

POSITIVE LOGITS

 praised

0.68

 vanwege

0.55

 своими

0.53

 noted

0.53

 praise

0.52

 своей

0.50

 zbog

0.50

 applauded

0.48

 admired

0.48

 pelas

0.48

Activations Density 0.027%