INDEX

Explanations

expressing uncertainty or possibility

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

usually

0.37

 usually

0.34

Usually

0.33

۔

0.33

 Usually

0.33

Almost

0.33

幾乎

0.33

 Almost

0.32

 обычно

0.31

 meestal

0.31

POSITIVE LOGITS

 algún

0.59

 irgende

0.51

 alguna

0.49

 algum

0.48

 nějak

0.46

某种

0.46

 alguma

0.46

 qualche

0.45

 jakieś

0.44

 κάπο

0.43

Activations Density 0.229%