INDEX

Explanations

This neuron fires on uppercase identifiers—short all-caps tokens and single-letter capital variables commonly found in code.

CSV, WS, js, Dim, OS, Ui, Reset, Inner

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

 only

-1.36

for

-1.21

-1.14

 shouldn

-1.10

 just

-1.09

-1.06

 what

-1.03

 with

-1.02

 aspects

-1.00

POSITIVE LOGITS

âtel

1.26

modium

1.20

opies

1.19

́

1.17

蛲

1.16

Utiliz

1.16

']),

1.16

)]);

1.15

ミカ

1.14

ŚĆ

1.14

Activations Density 0.121%