INDEX

Explanations

stick, rod, cane, staff

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

 scissors

-0.10

coin

-0.10

 knife

-0.10

âĶ´

-0.10

Wie

-0.09

knife

-0.09

 sheet

-0.09

 coin

-0.09

atsu

-0.09

 punched

-0.09

POSITIVE LOGITS

 stick

0.28

rod

0.25

 sticks

0.24

 rods

0.24

 Stick

0.22

 cane

0.22

æĿ

0.22

Rod

0.21

stick

0.21

 staff

0.21

Activations Density 0.062%