INDEX

Explanations

introducing descriptive text:

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

ï½§

-0.09

>NN

-0.09

abee

-0.08

Hra

-0.08

/Dk

-0.08

Truthy

-0.08

MDB

-0.08

UCKET

-0.08

 recomm

-0.08

antz

-0.08

POSITIVE LOGITS

onet

0.09

sup

0.08

 practices

0.08

CST

0.08

resa

0.08

""

0.08

 steward

0.07

Â¨

0.07

obo

0.07

APH

0.07

Activations Density 0.095%