INDEX

Explanations

import statements

The neuron is specialized in detecting ES6-style import statements (the “import” keyword).

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

 with

-1.55

by

-1.52

 when

-1.51

you

-1.45

 your

-1.45

 which

-1.39

 utterly

-1.24

 sadly

-1.23

 When

-1.21

好評

-1.21

POSITIVE LOGITS

weren

1.56

 WENT

1.52

wasn

1.52

began

1.51

ighed

1.51

became

1.49

jusqu

1.49

 hade

1.48

鹟

1.47

椟

1.43

Activations Density 0.023%