INDEX

Explanations

In Commission v NAME_1

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

 Kushner

-0.10

vig

-0.09

DIN

-0.09

 allegation

-0.09

 Bent

-0.09

uesta

-0.09

ä¿

-0.08

 bent

-0.08

 respected

-0.08

rec

-0.08

POSITIVE LOGITS

 case

0.21

 cases

0.19

case

0.16

æ¡Ī

0.16

 landmark

0.16

 Case

0.16

 pÅĻÃŃpad

0.15

cases

0.14

Case

0.14

Activations Density 0.040%