INDEX

Explanations

moon landing on July 20

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

 Lionel

-0.13

 Weinstein

-0.10

_NOP

-0.09

 Sant

-0.09

 Martian

-0.09

 taper

-0.09

 rollers

-0.09

 Dickens

-0.09

 drone

-0.09

akin

-0.08

POSITIVE LOGITS

 landing

0.21

 Buzz

0.20

 Apollo

0.20

 Landing

0.20

 Neil

0.19

Buzz

0.17

 Armstrong

0.17

 landed

0.17

landing

0.16

Neil

0.16

Activations Density 0.025%