INDEX

Explanations

places or things described

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

uming

-0.09

SSI

-0.09

 Dahl

-0.09

/cgi

-0.08

asca

-0.08

 bach

-0.08

uchar

-0.08

 Grim

-0.08

osemite

-0.08

 CALLBACK

-0.08

POSITIVE LOGITS

 itself

0.14

à¹Ģà¸Ńà¸ĩ

0.13

æĺ¯ä¸Ģä¸ª

0.12

æĺ¯ä¸ª

0.12

 happen

0.12

 themselves

0.11

åĲį

0.11

 Happ

0.10

 concerned

0.10

 happened

0.10

Activations Density 0.193%