INDEX

Explanations

Source determination

This neuron fires on numbered document section headings—e.g. “2. Implemented Features,” “Case Reports,” “Purpose,” etc.

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

 even

-1.61

in

-1.54

—

-1.40

 даже

-1.33

 sogar

-1.33

if

-1.32

and

-1.32

for

-1.28

さらに

-1.22

¶

-1.22

POSITIVE LOGITS

 about

1.42

 gestartet

1.28

 ambass

1.28

 recupero

1.27

 meestal

1.27

Története

1.25

 atacado

1.24

 禁止

1.23

 ottenuto

1.23

 discogs

1.21

Activations Density 0.215%