INDEX

Explanations

foreign words and court documents

The neuron fires strongly on multi‐digit numeric tokens (long sequences of digits, like years or docket numbers).

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

by

-1.56

in

-1.43

all

-1.38

on

-1.23

 because

-1.20

any

-1.17

one

-1.15

can

-1.15

 from

-1.14

 every

-1.06

POSITIVE LOGITS

為に

1.29

すっ

1.20

튿

1.10

1.09

 otwor

1.08

 tôt

1.06

 trám

1.05

 uitzicht

1.05

凄い

1.03

 жк

1.03

Activations Density 0.019%