INDEX

Explanations

references to the initial step or phase in a process or sequence

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

 Starts

-1.45

 starts

-1.43

 begins

-1.40

 Begins

-1.40

 begin

-1.37

begins

-1.37

 start

-1.36

 Beginning

-1.36

 Starting

-1.35

 beginnings

-1.34

POSITIVE LOGITS

 first

1.37

first

1.14

First

1.13

 First

1.13

FIRST

1.02

 FIRST

0.97

 dulu

0.78

 dahulu

0.76

 primero

0.73

先

0.73

Activations Density 0.218%