INDEX

Explanations

divider character for lists

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

Äı

-0.09

icari

-0.08

ÄĤ

-0.08

rello

-0.08

igel

-0.08

osu

-0.08

 Ø¢Ø°

-0.08

ÅĻiv

-0.07

fcc

-0.07

ð

-0.07

POSITIVE LOGITS

 unknown

0.13

 none

0.13

 None

0.12

unknown

0.11

 NONE

0.10

ãĢĢãĢĢãĢĢãĢĢ ãĢĢ

0.10

None

0.09

 rowspan

0.09

ä¸įçŁ¥

0.09

 Other

0.09

Activations Density 0.136%