INDEX

Explanations

Legal case names

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

ç»ĵ

-0.33

ç²¾ç¾İ

-0.30

çµĲ

-0.29

ä¸ĭè¡Į

-0.28

rego

-0.25

éĻ¢

-0.25

æĪĲçĨŁçļĦ

-0.25

 motives

-0.24

ums

-0.24

 enact

-0.24

POSITIVE LOGITS

 TOUR

0.27

ourse

0.27

[[]

0.26

 directly

0.25

-only

0.25

@author

0.24

.addTab

0.24

 Tour

0.24

åı¯ä¿¡

0.23

aman

0.23

Activations Density 0.004%