INDEX

Explanations

accomplishments and contributions

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

for

-2.75

 what

-2.41

 from

-2.41

as

-2.22

 there

-2.19

if

-1.85

all

-1.78

 more

-1.72

 with

-1.70

 every

-1.63

POSITIVE LOGITS

 faciliter

1.47

跟他

1.46

 siè

1.42

 mépris

1.40

 représenter

1.38

 engend

1.38

 citroen

1.37

 corrom

1.37

 várias

1.34

 fré

1.34

Activations Density 0.053%