INDEX

Explanations

my followed by custom class names

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

you

-2.17

 jestli

-1.89

来自于

-1.86

is

-1.75

 they

-1.73

 mães

-1.72

</h4>

-1.70

slut

-1.69

say

-1.68

 órgãos

-1.67

POSITIVE LOGITS

The

2.56

<h2>

2.16

new

2.09

徜

2.05

"—

1.99

1.90

As

1.87

1.85

 همچ

1.80

.''

1.78

Activations Density 0.027%