INDEX

Explanations

This neuron detects section headings or highlighted feature titles (e.g. product-listing headers and label phrases) in the text.

regular expressions or code comments

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

 there

-1.45

jā

-1.39

 immediately

-1.39

 where

-1.33

 their

-1.33

 begins

-1.32

 alterations

-1.30

 altering

-1.28

it

-1.27

ādi

-1.26

POSITIVE LOGITS

，

1.51

；

1.42

 your

1.34

（

1.26

1.20

。

1.13

 auxquels

1.12

：

1.09

َ

1.09

「

1.07

Activations Density 0.019%