INDEX

Explanations

introducing purpose or consequence

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

 because

-1.57

and

-1.55

 eftersom

-1.43

 since

-1.40

 that

-1.38

 dlatego

-1.27

 omdat

-1.23

 потому

-1.16

 ponieważ

-1.15

 protože

-1.13

POSITIVE LOGITS

 they

2.31

we

1.92

 cuando

1.75

 ketika

1.73

 можно

1.69

 lorsque

1.64

can

1.59

 nantinya

1.59

 later

1.57

 można

1.53

Activations Density 0.029%