INDEX

Explanations

years ranges

The neuron strongly activates on en‐dashes or hyphens used in date and number ranges (e.g. “1952–57” or “–1960”).

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

 which

-1.30

 whose

-1.28

as

-1.27

any

-1.16

at

-1.16

 using

-1.16

 spurred

-1.09

 used

-1.08

 with

-1.06

 unique

-1.06

POSITIVE LOGITS

 AMAZING

1.20

 soooo

1.15

 sooo

1.12

ほとん

1.08

UNICIP

1.05

allows

1.04

bbie

1.03

 компания

1.02

 alcune

1.02

 alcuni

1.02

Activations Density 0.021%