INDEX

Explanations

issue of [specific noun]

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

 controladores

-1.62

 hilos

-1.50

 trám

-1.45

鸶

-1.39

 entidades

-1.39

もありました

-1.38

 getan

-1.37

 ajedrez

-1.36

Ruj

-1.35

 Traducción

-1.33

POSITIVE LOGITS

by

1.73

 where

1.45

1.31

1.30

 which

1.27

“

1.23

on

1.21

1.20

ik

1.17

 having

1.16

Activations Density 0.045%