INDEX

Explanations

this followed by item

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

了个

-1.45

 eenig

-1.45

翆

-1.37

∝

-1.34

SUM

-1.31

 destinés

-1.30

<",

-1.30

ленного

-1.28

ter

-1.27

 следующий

-1.27

POSITIVE LOGITS

if

2.00

 when

1.95

by

1.94

 with

1.59

From

1.47

 which

1.46

 from

1.45

 perhatian

1.41

 before

1.41

</b>

1.41

Activations Density 0.041%