INDEX

Explanations

Copyright notices

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

汤

-0.69

RANDOM

-0.68

 Gazette

-0.68

saver

-0.68

ICIOS

-0.68

 软件

-0.67

 Pandit

-0.67

ęki

-0.67

 Kathmandu

-0.67

antium

-0.66

POSITIVE LOGITS

 chivalry

0.68

 alá

0.65

Marble

0.65

hommes

0.64

 homogen

0.63

 itinerary

0.63

 markdown

0.63

Lyn

0.61

 vár

0.61

firing

0.60

Activations Density 0.041%