INDEX

Explanations

utility and service imports

The neuron activates on identifiers in module or package import (and package) declarations, i.e. it detects fully-qualified names in import/package statements.

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

 then

-1.35

if

-1.30

to

-1.27

If

-1.25

in

-1.23

 אם

-1.16

 непосредственно

-1.14

 using

-1.13

cted

-1.11

ůr

-1.10

POSITIVE LOGITS

disposing

1.44

≒

1.30

こちらも

1.30

 trono

1.27

 которая

1.24

畱

1.23

 felpa

1.21

ของคุณ

1.19

 lema

1.17

 pegatinas

1.16

Activations Density 0.055%