INDEX

Explanations

sequences and cycles

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

 completion

-0.88

onuclear

-0.84

acci

-0.81

rotech

-0.81

other

-0.81

 finishing

-0.80

代わりに

-0.79

 Uncategorized

-0.78

 extrapolation

-0.78

eno

-0.77

POSITIVE LOGITS

 then

1.95

 потім

1.56

 repeatedly

1.42

然后

1.39

然後

1.37

 ثم

1.36

 alternating

1.29

Then

1.29

 alternately

1.27

 tekrar

1.26

Activations Density 0.062%