INDEX

Explanations

programming keywords

The neuron detects leading indentation whitespace (tabs/spaces) at the start of code lines.

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

なんだけど

-0.92

 your

-0.90

ньому

-0.86

my

-0.85

 that

-0.83

Jeśli

-0.80

our

-0.79

 ännu

-0.78

xture

-0.77

POSITIVE LOGITS

 void

2.42

void

2.31

 bool

1.56

bool

1.49

 voids

1.22

 const

1.13

 будет

1.13

inline

1.05

const

1.00

std

0.92

Activations Density 0.009%