INDEX

Explanations

connection and feelings

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

 presum

-0.10

 brides

-0.09

 Buster

-0.09

éŁ¿

-0.09

itol

-0.08

 Proxy

-0.08

 memory

-0.08

 micron

-0.08

 Budd

-0.08

-r

-0.08

POSITIVE LOGITS

 relationship

0.13

 reunion

0.12

 future

0.12

loff

0.11

 currently

0.10

tar

0.10

relationship

0.10

 Toxic

0.10

future

0.10

Latch

0.10

Activations Density 0.028%