INDEX

Explanations

remaining and saving words

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

臜

-3.56

uſe

-2.39

навли

-2.30

But

-2.27

 encuentras

-2.19

 Reſ

-2.14

 PUSTAKA

-2.13

 quieren

-2.11

蔸

-2.08

POSITIVE LOGITS

↵

3.25

2.64

2.36

2.02

เกง

1.97

ского

1.95

。。。。

1.90

_;

1.90

　　……

1.88

ine

1.86

Activations Density 0.001%