INDEX

Explanations

a followed by nouns

The neuron consistently fires on the single-letter indefinite article “a.”

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

Leírás

-1.91

-1.86

or

-1.58

𐄙

-1.54

CurtirCurtir

-1.48

 spannende

-1.42

Uhm

-1.41

ープン

-1.40

Gruppe

-1.39

Musik

-1.38

POSITIVE LOGITS

1.66

way

1.54

だろ

1.53

 carnet

1.46

 моменты

1.44

>');

1.44

now

1.40

哧

1.40

かもし

1.39

 свадеб

1.39

Activations Density 0.030%