INDEX

Explanations

binary tree traversals

The neuron detects references to tree data structures and their components (e.g. “Tree,” “Node,” “left,” “right”).

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

哪怕

-1.29

ěstí

-1.28

 même

-1.28

–

-1.21

 również

-1.20

 vẫn

-1.16

詳細は

-1.15

arul

-1.12

丘

-1.10

Â

-1.08

POSITIVE LOGITS

 trees

1.41

嘔

1.25

lıyor

1.23

ález

1.21

onLoad

1.20

雌

1.20

man

1.19

 luces

1.17

 atenta

1.17

mpada

1.16

Activations Density 0.003%