INDEX

Explanations

XML tags, comments, C# attributes, or natural language sentences

This neuron detects numeric literals (numbers, including integers and floats) in code and data.

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

its

-1.65

by

-1.53

all

-1.48

in

-1.45

of

-1.41

two

-1.38

 their

-1.38

 that

-1.36

for

-1.34

 more

-1.31

POSITIVE LOGITS

,;

1.28

 ebenfalls

1.27

 также

1.25

なども

1.25

 некоторых

1.23

 REALLY

1.23

vd

1.22

 нашим

1.20

 várias

1.19

 delightfully

1.19

Activations Density 0.000%