INDEX

Explanations

free will and freelance

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

loo

-0.10

 vested

-0.10

 Spicer

-0.10

 Robbins

-0.10

 Hicks

-0.09

mani

-0.09

Rue

-0.09

cn

-0.09

 flatt

-0.09

sm

-0.09

POSITIVE LOGITS

bie

0.20

bsd

0.17

form

0.17

 lance

0.17

-standing

0.17

hand

0.17

zers

0.16

hold

0.16

bies

0.16

boot

0.16

Activations Density 0.016%