INDEX

Explanations

big/little concepts

This neuron highlights relatively rare, content-rich words (i.e. words with high inverse document frequency) rather than common function words.

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

as

-2.13

 both

-1.68

or

-1.55

 również

-1.55

by

-1.45

its

-1.34

on

-1.33

蜗

-1.32

 arī

-1.30

 either

-1.23

POSITIVE LOGITS

なぜ

1.46

次は

1.41

/>";

1.41

 />";

1.38

 těch

1.37

 obyvateľov

1.34

 beſt

1.34

なんとなく

1.34

/";

1.33

 lefs

1.33

Activations Density 0.104%