INDEX

Explanations

OpenGL graphics and mathematics

This neuron fires on programming‐language tokens—especially code identifiers, keywords, and OpenGL/API function names.

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

ּוֹ

-1.36

AFFIRMED

-1.32

 process

-1.30

ְּ

-1.29

gridColumn

-1.20

 Acesso

-1.15

pherds

-1.15

 from

-1.13

 Início

-1.13

只有

-1.12

POSITIVE LOGITS

ῖν

1.39

ׇ

1.36

 chimie

1.29

 войне

1.27

')'

1.25

 religieuse

1.23

 chré

1.22

 sufrido

1.21

 religieuses

1.16

 температуре

1.16

Activations Density 0.005%