INDEX

Explanations

phrase segmentation

The neuron activates on numeric tokens (e.g. integers or decimals), effectively detecting numbers in the text.

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

and

-1.13

腭

-1.12

at

-1.04

～～

-1.02

’)

-1.00

”

-0.97

or

-0.95

<>

-0.94

 then

-0.93

 保証

-0.91

POSITIVE LOGITS

ようになって

1.31

 llavero

1.28

soph

1.20

あー

1.20

 sogget

1.17

 engran

1.17

 normalmente

1.16

 logotipo

1.14

𒊹

1.13

ANCO

1.13

Activations Density 0.316%