INDEX

Explanations

raw data, material, or file

This neuron detects occurrences of the standalone word “raw” (in any casing).

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

’

-2.59

</h3>

-2.50

-2.20

也会

-2.16

やった

-2.13

-2.08

in

-2.05

 ส่วน

-2.03

],

-1.96

POSITIVE LOGITS



2.58

他自己

2.38

௜

2.28

 multitude

2.27

 mereka

2.25

鷓

2.23

しくお願い

2.11

utterstock

2.11

嘬

2.09

subsection

2.08

Activations Density 0.013%