INDEX

Explanations

are verb following concepts

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

 ÑģÑĤÐ°Ð½ÐµÑĤ

-0.14

 Ø¨Ø§Ø´Ø¯

-0.13

be

-0.13

was

-0.13

 wasn

-0.13

ÑĩÐ¸Ð²Ð°ÐµÑĤÑģÑı

-0.12

was

-0.11

_was

-0.11

ÑĥÐµÑĤÑģÑı

-0.11

 Ø´ÙĪØ¯

-0.11

POSITIVE LOGITS

are

0.42

 jsou

0.30

 sÄħ

0.28

 ÙĩØ³ØªÙĨØ¯

0.28

 aren

0.28

 sÃ£o

0.28

 were

0.27

 sont

0.24

 zijn

0.24

 sono

0.24

Activations Density 0.319%