INDEX

Explanations

focus on aspects

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

egis

-0.10

 favour

-0.09

oren

-0.09

 favor

-0.09

iges

-0.09

emm

-0.08

 Faster

-0.08

ongo

-0.08

 stand

-0.08

 spokes

-0.08

POSITIVE LOGITS

 rather

0.27

rather

0.22

 instead

0.17

 Rather

0.17

 aspect

0.17

 aspects

0.16

èº«ä¸Ĭ

0.14

Rather

0.14

 alone

0.13

aspect

0.13

Activations Density 0.164%