INDEX

Explanations

punctuation and symbols

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<eos>

1.14

 继续访问

0.88

↵↵↵↵↵↵↵↵↵↵↵↵↵↵

0.67

</code>

0.64

 Below

0.63

</h1>

0.63

↵↵

0.61

 }}$.

0.61

<unused60>

0.59

↵↵↵↵↵↵↵↵↵↵

0.58

POSITIVE LOGITS

”、“

2.33

.;

2.22

$;

2.18

!;

2.18

;

2.16

 Gresham

2.13

”;

2.05

/;

2.04

；

2.00

﹔

1.98

Activations Density 0.142%