INDEX

Explanations

variant and variations

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

櫺

-1.45

┮

-1.27

 Aleksandra

-1.24

 prosegu

-1.23

 varietà

-1.20

覿

-1.19

踽

-1.16

⽼

-1.16

檍

-1.16



-1.14

POSITIVE LOGITS

in

1.35

and

1.14

the

1.14

 Very

1.12

If

1.06

*.

1.05

 Being

1.04

To

1.04

 From

1.03

 Here

1.02

Activations Density 0.033%