INDEX

Explanations

The neuron fires on the appearance of the trigonometric sine function (the token “Sin” in code).

specific phrase beginnings

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

וּ

-1.77

ּוֹ

-1.74

 бампер

-1.59

וּ

-1.41

 колба

-1.32

to

-1.32

᾿

-1.25

ְּ

-1.22

ֶּ

-1.21

־ה

-1.21

POSITIVE LOGITS

ׇ

1.76

֩

1.40

 گیاه

1.37

 מים

1.34

 cukru

1.30

 ویتامین

1.27

 katholischen

1.23

 tidligere

1.21

وكان

1.20

 државе

1.19

Activations Density 0.000%