INDEX

Explanations

people and their connections

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

-0.11

ista

-0.11

-0.09

iesta

-0.09

izzle

-0.09

 ioctl

-0.09

olist

-0.09

uer

-0.09

aries

-0.09

CLU

-0.09

POSITIVE LOGITS

hood

0.19

 mover

0.13

 Places

0.12

 pleasing

0.12

kind

0.11

Soft

0.11

 smugg

0.11

opause

0.11

affen

0.11

connexion

0.11

Activations Density 0.048%