INDEX

Explanations

opinions and accordingly

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

 yeri

-1.02

 Février

-0.98

 pét

-0.96

 lakini

-0.95

 litoral

-0.94

 Scrolls

-0.91

 tjen

-0.90

 Décembre

-0.89

 destiné

-0.89

 botines

-0.88

POSITIVE LOGITS

see

2.08

see

1.66

See

1.53

cf

1.45

 Accordingly

1.38

 sees

1.37

 accordingly

1.29

See

1.27

Cf

1.24

 sehen

1.14

Activations Density 0.014%