INDEX

Explanations

making achievements

The neuron fires on the verb “make” (and its forms like made, making), especially in constructions like “made it.”

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

 będ

-1.38

ㆆ

-1.38

₤

-1.37

ATHAN

-1.35

 odası

-1.34

┇

-1.34

 électriques

-1.33

 本店

-1.30

Т

-1.30

 personnaliser

-1.29

POSITIVE LOGITS

1.54

 such

1.40

 like

1.34

</b>

1.30

 what

1.23

 می‌توان

1.23

de

1.20

]};

1.12

 Banyak

1.11

grandchildren

1.09

Activations Density 0.016%