INDEX

Explanations

explanation or specifications

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

 stets

0.30

 svet

0.27

 стреми

0.27

 pleasures

0.26

 contentment

0.26

 gratification

0.25

 lutte

0.25

 چنین

0.25

 stillness

0.25

 muros

0.25

POSITIVE LOGITS

 actually

0.33

其他的

0.28

 później

0.28

 referenced

0.28

referenced

0.27

 显示

0.26

 totiž

0.25

uradaki

0.25

 indirectly

0.25

called

0.25

Activations Density 0.000%