INDEX

Explanations

identifiers starting with underscore

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

_{

-2.30

 coloridos

-2.19

眼底

-2.16

 cromado

-2.14

 magnética

-2.13

-2.11

 colorido

-2.09

趼

-2.09

la

-2.08

 animados

-2.06

POSITIVE LOGITS

>"+

2.73

ꪹ

2.52

to

2.44

鲠

2.39

 Перейти

2.34

 ながら

2.28

2.23

′-

2.23

 одним

2.22

(_

2.17

Activations Density 0.002%