INDEX

Explanations

turning points and moments

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

 uphe

-0.09

igrams

-0.09

amba

-0.09

ardu

-0.08

Ľå»º

-0.08

 UIControl

-0.08

rise

-0.08

urb

-0.08

centers

-0.08

ifen

-0.08

POSITIVE LOGITS

 turning

0.50

 Turning

0.38

 turn

0.33

turn

0.29

Turning

0.29

 fork

0.27

-turn

0.27

 TURN

0.26

 moment

0.26

 turned

0.25

Activations Density 0.101%