INDEX

Explanations

mathematical projection

This neuron detects mentions of projecting or projection operations (i.e. the words “project”/“projection”).

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



-1.76

 ними

-1.49

↵↵

-1.48

 Física

-1.45

ológicas

-1.45

？）

-1.44

 APPELLANT

-1.41

 القديمة

-1.40

 infuriating

-1.37

-1.35

POSITIVE LOGITS

 your

1.59

to

1.48

 everybody

1.37

1.34

the

1.33

↵

1.29

 from

1.27

1.23

you

1.22

 ſta

1.22

Activations Density 0.041%