INDEX

Explanations

word formation

This neuron detects identifier or constant fragments that begin with an uppercase letter (e.g. CamelCase/PascalCase segments and all-caps names) 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

in

-1.12

any

-1.11

 every

-1.06

 most

-1.05

obé

-1.02

～！

-1.01

 Grüßen

-1.00

imbangan

-1.00

 many

-1.00

at

-1.00

POSITIVE LOGITS

様に

1.14

事が

1.09

ほうが

1.05

ance

1.05

帰って

1.05

嬸

1.05

сторінку

1.03

.‏

1.02

AndFlush

1.01

様な

1.00

Activations Density 0.101%