INDEX

Explanations

as opposed to / compared to

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

 shoe

-0.94

mischen

-0.83

 kertoo

-0.82

 Orbit

-0.80

neho

-0.79

ｅ

-0.79

 nagu

-0.77

ᄆ

-0.77

fractive

-0.75

塵

-0.75

POSITIVE LOGITS

 opposed

6.88

opposed

4.81

 oppose

3.56

 opposes

2.78

 versus

2.72

 oposición

2.36

 oppos

2.31

 rather

2.31

vs

2.25

 compared

2.22

Activations Density 0.030%