INDEX

Explanations

violent imagery or descriptions

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

፨

-2.50

The

-2.42



-2.39

⇹

-2.34

OF

-2.31

蒾

-2.30

।

-2.28

 และ

-2.25

༑

-2.25

⇿

-2.22

POSITIVE LOGITS



2.67

骓

2.66

))$_

2.45

 erklär

2.44

Only

2.44

 zusätzliche

2.33

ကိုးကား

2.27

 キャンペーン

2.23

»:

2.20

 grüne

2.20

Activations Density 0.003%