INDEX

Explanations

special characters and non-English words

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

 ulaÅŁ

-0.09

 weiber

-0.08

ldkf

-0.08

 dejtingsaj

-0.08

 -*-č\n

-0.08

Å®

-0.08

ÐĤ

-0.08

 htmlentities

-0.08

ÏģÎº

-0.08

krv

-0.08

POSITIVE LOGITS

es

0.09

 cá»§a

0.09

apÄ±

0.08

for

0.08

less

0.08

 Plantae

0.08

 Ãĸr

0.08

lh

0.08

.Cryptography

0.07

Activations Density 0.078%