INDEX

Explanations

certain [specific noun]

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

そんなに

-2.17

絰

-1.98

鼉

-1.94

鵙

-1.84

 adatta

-1.82

接过

-1.80

 creat

-1.80

ጐ

-1.79

⬈

-1.74

たまた

-1.73

POSITIVE LOGITS

</h3>

2.31

</em>

2.22

).

2.05

in

1.96

’,

1.83

 هستند

1.78

”,

1.73

 excellent

1.70

她

1.64

</strong>

1.61

Activations Density 0.018%