INDEX

Explanations

discovered, identified, found

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

.TryParse

-0.27

ths

-0.27

alg

-0.26

 projections

-0.26

akedown

-0.26

Alg

-0.26

Alg

-0.24

 prosecuting

-0.24

Algorithm

-0.24

 Algorithm

-0.24

POSITIVE LOGITS

 recently

0.31

 found

0.31

 discovered

0.30

ä¸ĢæĿ¡

0.28

 Recently

0.28

 Found

0.27

åıĳçİ°

0.27

found

0.26

ä¸Ģç§į

0.26

 Recent

0.26

Activations Density 0.006%