INDEX

Explanations

here is a

The neuron detects directive/presentational phrases—places where the speaker offers, presents, or urges something (e.g. “have some more,” “take this as,” “here is a …”).

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

 certamente

-1.30

の違い

-1.20

をよく

-1.20

刧

-1.18

 exclusivamente

-1.17

complish

-1.16

utusan

-1.16

 minat

-1.16

how

-1.15

 thereafter

-1.14

POSITIVE LOGITS

1.55

1.35

1.29

los

1.17

了出去

1.16

Ἀ

1.15

 ellas

1.14

hljs

1.13

");

1.12

Activations Density 0.050%