INDEX

Explanations

Here are some

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

quier

-0.10

 Portug

-0.08

 Shepherd

-0.08

ãĢı\n\n

-0.08

 Peaks

-0.08

 Pearce

-0.08

 “;

-0.07

 Leban

-0.07

eyed

-0.07

POSITIVE LOGITS

TypeInfo

0.10

 Ð¸Ð½ÑĦÐ¾ÑĢÐ¼Ð°

0.09

 Webster

0.08

ãģĿãģ®ä»ĸ

0.08

 zipfile

0.08

/simple

0.08

swer

0.08

masters

0.08

 answer

0.08

 Instance

0.08

Activations Density 0.391%