INDEX

Explanations

start or begin

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

Miz

-0.10

dn

-0.09

 reconc

-0.09

 loos

-0.09

 Rica

-0.09

 Rico

-0.08

def

-0.08

rien

-0.08

agh

-0.08

 laid

-0.08

POSITIVE LOGITS

 character

0.12

 role

0.10

 focus

0.10

 course

0.10

character

0.09

 Focus

0.09

role

0.09

 Roles

0.09

 Character

0.09

 Stay

0.09

Activations Density 0.010%