INDEX

Explanations

Estonian

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

 Serbian

-0.11

 Serbia

-0.11

 Austrian

-0.10

 Yugosl

-0.10

Lob

-0.10

 Czech

-0.10

 Bulgarian

-0.10

 Norwegian

-0.09

 turkey

-0.09

 Laurel

-0.09

POSITIVE LOGITS

 Latvia

0.30

 Tall

0.29

 Baltic

0.29

Lat

0.28

 Balt

0.27

Lat

0.26

 Estonia

0.25

 Eston

0.22

 Tart

0.21

lat

0.19

Activations Density 0.027%