INDEX

Explanations

nodes in bfs traversals

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

 Harmony

-0.75

 CLOUD

-0.71

èse

-0.71

 Владими

-0.71

갑

-0.68

⎛

-0.68

vá

-0.67

faced

-0.66

 minor

-0.66

 Habitat

-0.65

POSITIVE LOGITS

BFS

1.57

bfs

1.46

BFS

1.40

bfs

1.38

 enqueue

1.13

 queue

1.12

Enqueue

1.05

QUEUE

1.03

 breadth

1.03

 level

1.02

Activations Density 0.009%