INDEX

Explanations

roles and their activities

This neuron fires on terms referring to organizational entities, roles, resources, or services (e.g., staff, researchers, meetings, tools, services).

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

for

-1.84

-1.74

 about

-1.62

 bestimmten

-1.52

-1.48

-1.46

Other

-1.45

abaikan

-1.43

 only

-1.42

 four

-1.40

POSITIVE LOGITS

and

2.39

ssos

1.74

we

1.73

>-->

1.72

 penting

1.70

our

1.67

吡

1.58

тился

1.57

!</

1.54

镲

1.52

Activations Density 0.112%