INDEX

Explanations

references to levels of significance and attributes in various contexts

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

igel

-0.07

asti

-0.06

not

-0.06

bas

-0.06

Ã¤s

-0.06

da

-0.06

 Basically

-0.06

 Lots

-0.06

 SvÄĽt

-0.06

POSITIVE LOGITS

 anymore

0.10

nor

0.08

 necessarily

0.08

same

0.08

 same

0.08

 slightest

0.07

egree

0.07

 SAME

0.07

VERRIDE

0.07

idor

0.07

Activations Density 0.024%