INDEX

Explanations

The main thing this neuron does is find mentions of specific publication or media outlet names.

Forbes magazine

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

-1.70

-1.58

 they

-1.45

-1.40

 formar

-1.38

</i>

-1.37

),

-1.33

();)

-1.29

-1.28

in

-1.23

POSITIVE LOGITS

 Hift

1.47

さと

1.47

 Thiết

1.42

 Stopwatch

1.39

spectos

1.38

 内衣

1.36

 概要

1.36

 regalías

1.36

OUTUBE

1.34

 メニュー

1.34

Activations Density 0.007%