INDEX

Explanations

introducing new concepts or terms

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

 this

-1.53

 этих

-1.44

<bos>

-1.40

 этого

-1.39

ير

-1.33

 ваших

-1.31

 này

-1.24

送

-1.24

 keinerlei

-1.23

all

-1.20

POSITIVE LOGITS

in

1.91

 introduce

1.62

 introducir

1.59

 Introduce

1.52

 because

1.42

 introduces

1.40

 with

1.38

to

1.35

as

1.27

but

1.26

Activations Density 0.071%