INDEX

Explanations

dinosaur

references to dinosaurs, prehistoric creatures, and ancient time periods.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 Rats

-0.88

腋

-0.83

hoben

-0.80

 Dove

-0.77

otech

-0.77

 rats

-0.76

carpa

-0.76

sheep

-0.75

filesystem

-0.75

 Bats

-0.75

POSITIVE LOGITS

 dinosaur

2.91

 dinosaurs

2.77

 dino

2.41

 Dinosaur

2.25

 Dinosaurs

2.20

 Jurassic

2.13

 dinos

2.11

 prehistoric

2.06

Jurassic

1.98

dino

1.95

Activations Density 0.033%