INDEX

Explanations

function and code block definitions

The neuron specializes in detecting function definitions (e.g. the “def”, “function”, “func” keywords and their following parameter‐list parentheses) in code.

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

 soportar

-0.99

 recurrir

-0.96

grandes

-0.93

Cevap

-0.92

 comienzan

-0.88

 چی

-0.88

 oír

-0.87

 comenzar

-0.87

懷

-0.86

 mantenga

-0.85

POSITIVE LOGITS

 your

1.15

 هر

1.13

 each

1.07

our

1.05

\[

1.00

ؤية

0.94

any

0.93

0.92

ullar

0.91

<tr>

0.91

Activations Density 0.017%