INDEX

Explanations

import paths

The neuron fires on module specifier strings in import statements—i.e. the quoted path segments (especially relative paths) following “from.”

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

on

-1.44

but

-1.40

for

-1.30

 during

-1.27

use

-1.27

 entonces

-1.26

 only

-1.24

墮

-1.24

not

-1.20

 need

-1.20

POSITIVE LOGITS

different

1.50

loten

1.43

 شروع

1.42

 menyen

1.41

 différents

1.41

 annet

1.39

 bensin

1.37



1.34

sieren

1.34

 deſt

1.34

Activations Density 0.089%