INDEX

Explanations

contrasting conjunctions

The neuron flags uncommon, content-bearing words (especially longer, multisyllabic nouns and adjectives) 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

heiros

-0.85

iffen

-0.82

not

-0.81

╞

-0.79

fof

-0.79

—"

-0.77

つき

-0.77

Возраст

-0.76

Например

-0.76

 årene

-0.75

POSITIVE LOGITS

but

5.03

 nhưng

2.70

But

2.63

 แต่

2.47

But

2.38

 लेकिन

2.30

但

2.23

but

2.22

但是

2.17

 ولی

2.17

Activations Density 0.055%