INDEX

Explanations

specific nouns or descriptions

The neuron never activates on any tokens—it isn’t detecting any pattern.

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

ကိုးကား

-1.45

 this

-1.44

 like

-1.44

鹩

-1.41

 thereafter

-1.39

 लेकिन

-1.38

の高い

-1.37

 LIRE

-1.36

也会

-1.35

 çocuklar

-1.34

POSITIVE LOGITS

usive

1.79

1.70

uride

1.68

and

1.66

oys

1.64

usions

1.63

yled

1.62

iric

1.51

lllllll

1.50

antism

1.50

Activations Density 0.088%