INDEX

Explanations

discovery and finding

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

@student

-0.10

uated

-0.10

oldt

-0.09

ensibly

-0.09

eration

-0.09

 lasers

-0.09

jeme

-0.09

UNC

-0.08

ëĮ

-0.08

POSITIVE LOGITS

rir

0.14

erto

0.14

 discovery

0.13

 discover

0.13

 discovered

0.13

åıĳçİ°

0.13

ert

0.12

erte

0.12

 Discovery

0.11

rim

0.11

Activations Density 0.029%