INDEX

Explanations

numerical statistics embedded in text

two

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

Negative Logits

 ویکی‌آمباردا

-0.42

 estabiliz

-0.40

 sabun

-0.40

 gesteld

-0.40

altham

-0.39

äj

-0.38

 mueve

-0.38

 gravedad

-0.38

orith

-0.37

POSITIVE LOGITS

two

1.45

two

1.19

Two

1.18

Two

1.16

 three

1.13

TWO

1.11

TWO

1.07

 deux

1.06

 sixty

1.04

 fifty

1.00

Activations Density 18.901%