INDEX

Explanations

be followed by adjective

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

埽

-2.39

鼉

-2.30

闿

-2.13

""

-2.03

\},

-1.98

 événement

-1.96

());

-1.95

蘗

-1.93

+/**

-1.93

utes

-1.92

POSITIVE LOGITS

↵

2.94

be

2.88

It

2.38

鹮

2.31

2.09

 algunos

2.05

 Some

1.98

Because

1.95

<em>

1.93

 perennial

1.88

Activations Density 0.003%