INDEX

Explanations

data limits and selections

The neuron fires on tokens used to specify or limit the number of results (e.g. “top,” “take,” “head,” “limit”).

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

 propiet

-1.42

to

-1.40

 aspira

-1.39

یکر

-1.33

PSU

-1.32

 ronde

-1.31

 reforma

-1.30

OCH

-1.29

 hispan

-1.29

POSITIVE LOGITS

خوب

1.62

1.56

ممنون

1.55

 néhány

1.45

replyreport

1.37

わたしは

1.35

Nå

1.34

شما

1.34

 действительно

1.34

''

1.33

Activations Density 0.021%