INDEX

Explanations

phrases with "with" or "without"

The neuron responds to tokens that link or combine technical terms—like slashes (“/”), plus signs (“+”), “with,” “plus,” or similar connectors indicating relationships or combinations in scientific or structured text.

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

揍

-1.40

 procéder

-1.37

-1.33

 participer

-1.32

 faciliter

-1.30

-1.29

isn

-1.29

Ł

-1.28

 empêcher

-1.27

râ

-1.27

POSITIVE LOGITS

 without

2.16

 with

2.13

at

1.82

of

1.66

 will

1.58

as

1.56

 only

1.53

 heightened

1.52

by

1.49

 through

1.48

Activations Density 0.188%