INDEX

Explanations

Locations and political references

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

دل

-0.45

 Crimea

-0.44

익

-0.43

 converters

-0.43

 Panama

-0.43

 pyplot

-0.43

 converter

-0.42

"".

-0.42

 برس

-0.42

 Crimean

-0.41

POSITIVE LOGITS

ism

0.60

 Silla

0.59

uality

0.58

Tru

0.58

Rujuakan

0.57

 незавершена

0.57

RTLI

0.57

 Chopra

0.57

 gyhoeddwyd

0.56

icity

0.55

Activations Density 0.010%