INDEX

Explanations

code keywords and structures

This neuron detects .NET code attributes and namespace qualifiers (e.g. CompilerServices, GeneratedAttribute, InteropServices, DllImport) in source files.

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

 był

-1.48

 zarówno

-1.43

-1.38

 both

-1.34

 instead

-1.34

 each

-1.30

 either

-1.30

 eclectic

-1.27

 said

-1.25

 them

-1.24

POSITIVE LOGITS

 épices

1.55

ヶ

1.24

γρά

1.21

趿

1.18

kloped

1.17

Rote

1.17

EXIST

1.16

Veget

1.15

 premio

1.14

דת

1.14

Activations Density 0.003%