INDEX

Explanations

references to royal titles or related terms

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

memberOf

-0.07

 Elliot

-0.06

 convolution

-0.06

æľĭ

-0.06

/problems

-0.05

oxide

-0.05

nard

-0.05

INY

-0.05

conv

-0.05

POSITIVE LOGITS

 prince

0.10

 Prince

0.10

Prince

0.09

 jewel

0.09

edBy

0.09

 Jewel

0.08

 jewels

0.08

rani

0.08

edException

0.07

Jew

0.07

Activations Density 0.002%