phrases that indicate sources or authorship in descriptions

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

\_

-0.07

landa

-0.07

Ãły

-0.07

ÏģÎ±Î½

-0.07

Unnamed

-0.07

imary

-0.07

Ð¾Ð·Ð´

-0.06

Knife

-0.06

å¹³æĪĲ

-0.06

($)

-0.06

POSITIVE LOGITS

two

0.07

its

0.07

 saying

0.06

izoph

0.06

ovÃŃ

0.06

opes

0.06

 Fabric

0.06

 Bott

0.06

Activations Density 0.056%