INDEX

Explanations

sharing or giving freely

The neuron detects instances of the word “share” (in all its forms) indicating acts of sharing.

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

-1.78

my

-1.39

さんも

-1.38

 model

-1.36

to

-1.32

 control

-1.31

-1.30

 result

-1.26

 atriz

-1.26

 number

-1.25

POSITIVE LOGITS

When

1.52

 tanken

1.44

While

1.41

Although

1.40

merkungen

1.40

they

1.38

They

1.37

この日は

1.36

 різних

1.35

гії

1.34

Activations Density 0.014%