INDEX

Explanations

modeland model and actor/actress

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

 models

-0.31

models

-0.26

 Models

-0.24

_models

-0.24

.models

-0.22

Models

-0.22

 modeled

-0.21

 modelos

-0.21

 modelo

-0.21

/models

-0.21

POSITIVE LOGITS

âĶ´

0.10

 chili

0.10

/***/

0.09

 Chili

0.09

èªŀ

0.09

led

0.09

.addAttribute

0.09

tcb

0.09

/******/

0.09

RefCount

0.09

Activations Density 0.195%