INDEX

Explanations

identifying definitions

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

æĽ°

-0.10

 Tribe

-0.09

 tant

-0.09

vo

-0.09

 corresponding

-0.08

 temper

-0.08

 symbolism

-0.08

olan

-0.08

 Kendrick

-0.08

POSITIVE LOGITS

 refers

0.39

 refer

0.38

 referring

0.31

ref

0.29

refer

0.28

æĮĩ

0.27

Ref

0.24

 Refer

0.23

Refer

0.23

_refer

0.21

Activations Density 0.214%