INDEX

Explanations

hours of operation: if open

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

 Hanna

-0.10

 exotic

-0.10

 neutral

-0.10

 unarmed

-0.09

Cop

-0.09

 Delegate

-0.09

 vacation

-0.09

Delegate

-0.09

 promin

-0.09

 neutrality

-0.09

POSITIVE LOGITS

 secret

0.18

 authentic

0.17

off

0.17

 lesser

0.17

 authenticity

0.17

 quieter

0.16

 hidden

0.15

 Authentic

0.15

 away

0.15

 smaller

0.15

Activations Density 0.066%