INDEX

Explanations

code identifiers

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

on

-1.45

in

-1.31

 just

-1.14

 because

-1.08

 when

-1.07

 with

-1.07

any

-1.07

 what

-1.05

 When

-1.03

 seemingly

-0.99

POSITIVE LOGITS

 HARVARD

1.11

 ingenu

1.07

 Dinas

1.06

 ranting

1.06

 Hygge

1.05

 accla

1.05

ulfon

1.05

 NEGATIVE

1.05

 ENVIRONMENTAL

1.02

 incontro

1.02

Activations Density 0.025%