INDEX

Explanations

do anything

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

 similarly

-0.10

iani

-0.09

LOY

-0.09

 ï½°

-0.09

UGE

-0.09

alin

-0.08

 GOODMAN

-0.08

cq

-0.08

cret

-0.08

POSITIVE LOGITS

 anything

0.24

 everything

0.18

anything

0.16

ANY

0.16

 things

0.15

 Anything

0.15

ä»»ä½ķ

0.14

any

0.14

everything

0.13

 exactly

0.13

Activations Density 0.033%