INDEX

Explanations

begin

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 begin

-1.81

 begins

-1.71

beginning

-1.57

 beginning

-1.54

 Begin

-1.53

 began

-1.52

 Begins

-1.48

 Beginning

-1.47

Beginning

-1.45

begins

-1.42

POSITIVE LOGITS

to

0.80

 with

0.75

ness

0.68

with

0.60

its

0.57

 <<<<<<<<<<<<<<

0.57

 anew

0.56

 generating

0.54

sing

0.54

ing

0.53

Activations Density 0.054%