INDEX

Explanations

for all

The neuron is specialized to pick up LaTeX math‐mode formatting tokens—things like alignment markers (&, \\), commands such as “\text,” and the surrounding braces.

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

-1.57

注明

-1.45



-1.38

 später

-1.38

 údaje

-1.37

マニア

-1.32

𒊹

-1.30

ครื่อง

-1.29

Organisator

-1.28

 venido

-1.27

POSITIVE LOGITS

 both

1.58

all

1.50

</em>

1.41

termilk

1.40

ternut

1.38

 they

1.35

 those

1.34

 these

1.31

 each

1.31

Activations Density 0.019%