INDEX

Explanations

can generate

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

ryn

-0.09

 Decrypt

-0.09

DataContext

-0.09

sequences

-0.09

ActionResult

-0.08

ngth

-0.08

 crown

-0.08

 Fors

-0.08

 cler

-0.08

pek

-0.08

POSITIVE LOGITS

 auto

0.20

 Auto

0.18

 latent

0.16

Auto

0.16

auto

0.16

AE

0.16

 reconstruction

0.15

AE

0.15

 Reconstruction

0.15

cae

0.15

Activations Density 0.034%