INDEX

Explanations

numbered domain names

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

in

-1.61

 before

-1.44

In

-1.40

by

-1.39

all

-1.39

 eight

-1.35

any

-1.34

 most

-1.34

 four

-1.27

 seven

-1.27

POSITIVE LOGITS

 rác

1.57

 carregar

1.49

 trám

1.46

 ativar

1.38

 aleación

1.37

 lepší

1.32

sprzedam

1.31

 cóc

1.31

 ovlád

1.29



1.27

Activations Density 0.004%