INDEX

Explanations

app, video, users, computing

The neuron flags standalone label-style tokens—like section headings, metadata or category keys, and other field names in technical documents or code.

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

🫅

-1.34

不宜

-1.30

であれば

-1.28

sätzlich

-1.27

大约

-1.27

 САД

-1.26

 fondé

-1.25

IRQn

-1.24

НОЕ

-1.23

notifyListeners

-1.20

POSITIVE LOGITS

 your

1.33

 coppia

1.28

 totul

1.27

 parça

1.27

 devono

1.26

 viejas

1.25

觔

1.23

 riga

1.22

 vechi

1.22

 coveted

1.22

Activations Density 0.291%