INDEX

Explanations

identifiers after quotes or parens

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

 nowhere

-0.11

-0.10

::::::

-0.10

Guy

-0.10

.ribbon

-0.09

.jpg

-0.09

orm

-0.09

 Lorem

-0.09

POSITIVE LOGITS

my

0.21

My

0.17

 example

0.15

 test

0.14

My

0.14

my

0.14

\tmy

0.14

æĪĳçļĦ

0.14

example

0.13

nameof

0.12

Activations Density 0.108%