INDEX

Explanations

common name

The neuron is primarily triggered by occurrences of the word “name” (e.g. field labels like “name,” “short_name,” or “common name”).

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

who

-2.05

</u>

-1.62

 můžete

-1.46

in

-1.41

<blockquote>

-1.31

<h3>

-1.28

')

-1.27

 What

-1.27

̩

-1.25

’,

-1.23

POSITIVE LOGITS

of

1.24

 cauſe

1.23

mètre

1.21

 أخرى

1.19

谱

1.19

 سپس

1.18

 then

1.18

roo

1.14

öd

1.13

 այ

1.13

Activations Density 0.067%