INDEX

Explanations

multiple various sources

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

 Mellon

-0.10

ï¼Įæ¯ı

-0.09

olan

-0.09

iena

-0.09

andy

-0.09

_ne

-0.08

è½¯ä»¶

-0.08

 software

-0.08

oller

-0.08

ounded

-0.08

POSITIVE LOGITS

 multiple

0.23

any

0.20

 various

0.18

multiple

0.17

ANY

0.15

ä»»ä½ķ

0.15

ultiple

0.15

 Multiple

0.14

 anywhere

0.14

 several

0.14

Activations Density 0.108%