INDEX

Explanations

where followed by a subject

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

 短发

-2.16

for

-1.91

なのですが

-1.88

 内衣

-1.82

 póster

-1.80

なんですが

-1.67

 emocionante

-1.65

 Schluß

-1.64

because

-1.61



-1.58

POSITIVE LOGITS

we

2.16

ons

1.87

“

1.85

–

1.84

ing

1.73

om

1.73

 they

1.70

ho

1.67

ates

1.66

–

1.66

Activations Density 0.011%