INDEX

Explanations

rapid development and pace

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

asure

-0.10

beit

-0.10

-webpack

-0.10

ÐĤ

-0.09

egov

-0.09

anny

-0.09

/right

-0.09

uder

-0.08

abler

-0.08

riel

-0.08

POSITIVE LOGITS

-fire

0.23

 chÃ³ng

0.22

ity

0.18

idious

0.17

amente

0.15

ily

0.14

-response

0.14

 prot

0.13

 Prot

0.13

stm

0.13

Activations Density 0.018%