INDEX

Explanations

quantifiers before items

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

 materials

-0.96

 drzwi

-0.95

逃げ

-0.88

 flechas

-0.84

 продукции

-0.84

 veicolo

-0.83

 posibilidades

-0.82

 matériel

-0.82

 Publikum

-0.81

 solches

-0.81

POSITIVE LOGITS

 loaf

1.73

 pair

1.73

 bottle

1.39

pair

1.24

 packet

1.19

 dozen

1.14

 pairs

1.07

 batch

1.05

 sets

0.98

 gallon

0.98

Activations Density 0.055%