INDEX

Explanations

border or boundary

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

 surrounding

-0.11

IRQ

-0.10

fet

-0.10

à¸±à¸Ļà¸ĺ

-0.09

æĿŁ

-0.09

ãĥ³ãĤ°ãĥ«

-0.09

 devant

-0.09

 Surround

-0.09

loub

-0.09

 ::::::::

-0.08

POSITIVE LOGITS

 border

0.66

 Border

0.50

border

0.49

 borders

0.46

-border

0.46

Border

0.45

 boundary

0.42

 BORDER

0.39

_border

0.38

\tborder

0.36

Activations Density 0.102%