INDEX

Explanations

common prefixes of phrases

This neuron detects capitalized or proper‐noun tokens—i.e. words or abbreviations appearing with initial uppercase letters (often sentence-initial words, names, or acronyms).

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

 otros

-1.29

<bos>

-1.27

暧

-1.25

 aston

-1.23

そこで

-1.21

この

-1.17

 Arrondissement

-1.16

長さ

-1.15

 pittores

-1.14

我們

-1.13

POSITIVE LOGITS

1.39

 always

1.34

為に

1.26

 muszą

1.23

 wasn

1.23

 people

1.23

 something

1.22

1.20

 dużo

1.20

izing

1.20

Activations Density 0.094%