INDEX

Explanations

may be, can be, are selected

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

-2.25

of

-1.67

on

-1.59

 without

-1.38

so

-1.26

not

-1.23

 here

-1.23

at

-1.21

how

-1.18

-1.13

POSITIVE LOGITS

 Infantil

1.33

 gearbeitet

1.30

ENAS

1.28

྅

1.25

hanno

1.24

ḑ

1.23

liziert

1.20

 ankaŭ

1.20

zember

1.18

ギター

1.18

Activations Density 0.159%