INDEX

Explanations

latex package loading

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

枚目

-1.00

 ABSOL

-0.96

 certaines

-0.93

 Fourteen

-0.89

ATA

-0.89

 シルエット

-0.88

lievo

-0.87

nthesis

-0.86

 approxim

-0.85

 berücksichtigt

-0.84

POSITIVE LOGITS

ınız

1.09

 pourrais

0.99

 staunch

0.96

 Bearings

0.92

 reckless

0.86

 genuinely

0.86

 touted

0.85

 honestly

0.85

 unwavering

0.84

IANT

0.82

Activations Density 0.007%