INDEX

Explanations

Microsoft

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

èĬ±å¼Ģ

-0.31

 major

-0.29

.major

-0.28

imin

-0.27

Decoration

-0.27

 åıĤæķ°

-0.27

major

-0.26

åĽ½åľŁ

-0.26

ariat

-0.25

ä¹°åįķ

-0.24

POSITIVE LOGITS

 Windows

0.31

odu

0.28

.World

0.27

 Surface

0.27

èĥ¸

0.26

æĮł

0.26

Assets

0.26

Surface

0.25

formatted

0.25

 Research

0.25

Activations Density 0.013%