INDEX

Explanations

introducing side notes and questions

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

and

-1.26

hancers

-1.09

ёд

-1.06

salms

-1.00

 され

-0.99

<tbody>

-0.98

Xna

-0.97

॑

-0.97

ۡ

-0.96

]+

-0.96

POSITIVE LOGITS

1.66

 sebel

1.12

 Introducción

1.10

 régal

1.09

 katastro

1.09

Posté

1.07

 lauk

1.05

 bahwa

1.05

 bana

1.04

Tengo

1.03

Activations Density 0.020%