INDEX

Explanations

bookstores and booksellers

The neuron detects mentions of bookstores or book‐selling venues (e.g. “bookstore,” “bookstores,” “booksellers,” etc.).

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

 kimdir

-2.16

 verir

-1.95

◳

-1.90

鬓

-1.79

呖

-1.78

lardan

-1.77

 timmar

-1.75

 sayfa

-1.74

 venuto

-1.74

 Políticas

-1.73

POSITIVE LOGITS

</strong>

2.27

2.23

 this

2.17

ꦤ

1.76

 снимки

1.64

1.60

 którzy

1.59

<em>

1.59

1.56

 друзьями

1.55

Activations Density 0.007%