INDEX

Explanations

words within quotation marks

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

⿲

0.35

 testes

0.35

𝜌

0.35

blich

0.34

 deluge

0.34

 wrenches

0.33

 understandings

0.33

到達

0.32

cik

0.32

 reaches

0.32

POSITIVE LOGITS

샛

0.38

 eski

0.36

Surely

0.34

 Peter

0.33

 kellett

0.33

 childish

0.32

 Mortimer

0.32

 Nadia

0.31

 রোগের

0.31

 Spielen

0.31

Activations Density 0.019%