INDEX

Explanations

Planimetric, Nippon, Motorola, The

The neuron activates on programming‐ or markup‐style tokens (e.g. CSS values like “none,” template tags like “{%,” Vue/VuePress directives like “@keydown,” etc.).

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

 there

-1.48

際の

-1.29

 kämp

-1.28

 allerede

-1.27

 their

-1.27

際は

-1.27

 vín

-1.16

 "...

-1.16

konstruktion

-1.14

سيم

-1.13

POSITIVE LOGITS

 ",";

1.46

が

1.38

ch

1.22

al

1.14

で

1.13

を

1.13

se

1.11

 levering

1.09

に

1.05

1.04

Activations Density 0.000%