INDEX

Explanations

operators and arithmetic

This neuron fires on programming operator keywords (e.g. arithmetic and comparison operators like “divide,” “gte,” “add,” “and,” “xor”).

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

看过

-1.45

店主

-1.43

淦

-1.40

蟄

-1.34

最重要

-1.32

動物園

-1.32

 Contempor

-1.29

ных

-1.29

 députés

-1.27

聾

-1.27

POSITIVE LOGITS

1.80

 between

1.59

1.48

{}{}

1.44

1.43

TestingModule

1.42

1.41

about

1.38

 mellem

1.38

 tertinggi

1.34

Activations Density 0.011%