INDEX

Explanations

press releases

The neuron fires on uppercase abbreviations and acronyms (e.g. PRWEB, uint16) rather than ordinary words.

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

</h1>

-2.16

</b>

-2.13

↵

-2.03

</strong>

-1.99

-1.71

).

-1.70

"}}

-1.63

"}}>

-1.53

<i>

-1.53

又在

-1.47

POSITIVE LOGITS

囖

1.56

 honn

1.52

 vogli

1.52

снимок

1.51

 personali

1.50

 kafe

1.48

 brille

1.48

鱻

1.46

 visuel

1.45

 gide

1.44

Activations Density 0.000%