INDEX

Explanations

section followed by numbers

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

下载附件

-1.96

 presidencia

-1.88

꒦

-1.84

 catégories

-1.83

 écrire

-1.80



-1.77

 feuille

-1.73

 여성

-1.73

 épo

-1.71

afbeelding

-1.70

POSITIVE LOGITS

↵

2.67

》。

2.06

\"

1.98

''

1.90

\\

1.90

<bos>

1.88

1.85

 поскольку

1.84

re

1.81

”

1.80

Activations Density 0.015%