INDEX

Explanations

references to sections and methodologies in academic papers

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

Pik

-0.07

encies

-0.07

ä¹ħ

-0.06

éľ²

-0.06

Ìģ

-0.06

nu

-0.06

ite

-0.06

é¢ĺ

-0.06

ower

-0.06

ulp

-0.06

POSITIVE LOGITS

 section

0.32

 Section

0.27

section

0.27

 sections

0.27

-section

0.25

Section

0.25

 SECTION

0.24

_section

0.23

 subsection

0.23

.section

0.23

Activations Density 0.158%