INDEX

Explanations

's an example script

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

Mus

-0.10

OptionsResolver

-0.09

ovo

-0.09

 Garden

-0.09

 Ashe

-0.09

==-

-0.09

 printable

-0.08

¶Į

-0.08

mus

-0.08

 supern

-0.08

POSITIVE LOGITS

 code

0.12

 script

0.12

lua

0.11

 macro

0.11

yntax

0.11

 pseud

0.11

ä»£çłģ

0.10

 elseif

0.10

Lua

0.10

 variables

0.10

Activations Density 0.205%