INDEX

Explanations

also used in various

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

 Crist

-0.10

andal

-0.08

Fay

-0.08

igm

-0.08

quis

-0.08

âī§

-0.08

stras

-0.07

lashes

-0.07

Fe

-0.07

 erst

-0.07

POSITIVE LOGITS

 various

0.13

 Various

0.12

åĲĦç§į

0.12

aml

0.10

 wide

0.09

Various

0.09

à¸Ľà¸£à¸°à¹Ĥà¸¢à¸Ĭà¸Ļ

0.09

bagai

0.09

vox

0.09

 humans

0.09

Activations Density 0.260%