INDEX

Explanations

code syntax

The neuron fires on the arrow token “->” (e.g. in function return‐type annotations) 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

 Deinen

-1.54

狀況

-1.53

jewództ

-1.52

資訊

-1.51

無法

-1.51



-1.48

netbeans

-1.48

 Perseus

-1.43

日まで

-1.42

 тысячи

-1.41

POSITIVE LOGITS

 quando

1.59

1.47

噲

1.45

ie

1.44

 dann

1.38

高端

1.33

 Then

1.33

 platform

1.30

ية

1.29

Activations Density 0.002%