INDEX

Explanations

expressing belief or stating opinion

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

 also

-0.93

><

-0.85

 также

-0.84

@}

-0.84

āli

-0.82

 επίσης

-0.82

Xoa

-0.81

 devenue

-0.80

ڭ

-0.79

 when

-0.79

POSITIVE LOGITS

yes

1.80

yes

1.52

Yes

1.38

YES

1.34

YES

1.29

Yes

1.23

sì

1.11

 affirmative

1.08

 hacerlo

1.03

不行

1.03

Activations Density 0.084%