INDEX

Explanations

through leaves

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

 mushroom

-0.12

 Flower

-0.12

 flowering

-0.11

 Mushroom

-0.11

py

-0.11

 Floral

-0.11

flower

-0.11

 floral

-0.10

 flower

-0.10

 bloom

-0.09

POSITIVE LOGITS

 leaves

0.36

 Leaves

0.30

åı¶

0.27

 leaf

0.27

èĳī

0.25

 Leaf

0.22

 Ð»Ð¸ÑģÑĤÑĮ

0.22

Leaf

0.21

 leave

0.20

leaf

0.20

Activations Density 0.052%