INDEX

Explanations

css styling properties

The neuron activates on CSS property names (e.g. “text-align,” “font-family,” “font-size,” “white-space,” “margin-bottom”) in style attributes.

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

"،

-1.31

),

-1.26

’:

-1.21

ふと

-1.20

 gwaran

-1.20

},

-1.20

」，

-1.19

になれる

-1.18

できれば

-1.18

 jeśli

-1.18

POSITIVE LOGITS

<bos>

1.30

 ഒരു

1.13

 například

1.11

1.08

 великолеп

1.08

kiwa

1.05

now

1.05

 conmigo

1.03

Propel

1.02

 torsdag

1.02

Activations Density 0.002%