INDEX

Explanations

quantifying size and measurements

The neuron fires on uncommon, document-specific tokens—especially longer or technical words (e.g. function names, file paths, specialized jargon) that only appear once or very infrequently.

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

for

-1.80

at

-1.56

on

-1.41

as

-1.39

 eight

-1.37

 provide

-1.33

any

-1.30

 five

-1.30

 nine

-1.29

 after

-1.27

POSITIVE LOGITS

扨

1.48

㩒

1.34

めちゃくちゃ

1.34

 égale

1.31

 évidemment

1.29

 insanely

1.28

 arrêter

1.26

賸

1.25



1.25

 enraged

1.24

Activations Density 0.047%