INDEX

Explanations

code author names

The neuron detects Jupyter notebook JSON field names (e.g. “cell_type,” “execution_count,” “source,” 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

 painstaking

-1.47

 luxus

-1.46

 estaban

-1.46

 comprimidos

-1.43

 bagus

-1.41

Pemer

-1.39

ينما

-1.38

 músculo

-1.37

焢

-1.35

 lentes

-1.34

POSITIVE LOGITS

мым

1.74

illées

1.45

地在

1.43

onaise

1.41

;',

1.41

ificato

1.40

 gần

1.39

;$

1.37

’-

1.36

makeatletter

1.35

Activations Density 0.003%