INDEX

Explanations

colons

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

co

-0.45

 Stä

-0.44

><!--

-0.44

じゃないですか

-0.42

{@

-0.41

out

-0.41

zugehen

-0.41

ご

-0.40

zą

-0.40

FRA

-0.40

POSITIVE LOGITS

 bezeichneter

1.03

Datuak

1.00

جوايز

0.92

 autorytatywna

0.89

 يتيمه

0.87

 الحره

0.87

 beginnetje

0.86

TargetException

0.86

ViewFeatures

0.84

__':

0.84

Activations Density 0.003%