INDEX

Explanations

record and document history

New Auto-Interp

Top Features by Cosine Similarity

Configuration

Prompts (Dashboard)

10,000 prompts, 128 tokens each

Dataset (Dashboard)

lmsys/lmsys-chat-1m

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ACHI

-0.09

 Klan

-0.08

autop

-0.08

cloak

-0.08

sted

-0.08

 subscribed

-0.08

 taped

-0.08

 Moran

-0.08

<fieldset

-0.08

 Perc

-0.08

POSITIVE LOGITS

 record

0.51

 records

0.43

è®°å½ķ

0.36

record

0.34

 Record

0.33

 recording

0.33

 Records

0.31

records

0.30

 RECORD

0.30

 keeping

0.30

Activations Density 0.185%