INDEX

Explanations

e-commerce listing details

The neuron detects UI labels and metadata fields commonly found in online product listings (e.g. “Listing,” “Seller,” “Price,” “Rating,” “Orders,” etc.).

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

。

-1.41

atigable

-1.30

 Selatan

-1.28

 avenir

-1.27

nehmen

-1.27

٤

-1.24

出來的

-1.20

]!='

-1.20

=?";

-1.20

nesse

-1.19

POSITIVE LOGITS

 where

1.45

where

1.40

apj

1.35

埏

1.34

 already

1.33

our

1.32

糴

1.30

 utilisez

1.29

ktır

1.24

 longtime

1.23

Activations Density 0.034%