INDEX

Explanations

how to use

The neuron is responding to high‐frequency English function words (common “stop” words like but, it, is, to, use, more, common).

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

 this

-1.21

ञ

-1.05

ihnachts

-1.05

 everything

-1.00

 тази

-0.97

らなかった

-0.95

 quando

-0.94

ARGV

-0.93

آباد

-0.93

docx

-0.91

POSITIVE LOGITS

use

1.52

 using

1.46

使用

1.30

 استفاده

1.10

 gebruik

1.04

 воспользоваться

1.03

vyu

1.02

 sử

1.01

ToUse

1.01

 χρησιμοποι

0.98

Activations Density 0.117%