INDEX

Explanations

philosophical concepts or entities

The neuron activates on abstract, conceptual nouns (especially those ending in “-ence,” “-ion,” “-ology,” 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

 also

-1.60

ricians

-1.52

 particolarmente

-1.52

Leírás

-1.50

encers

-1.47

ございました

-1.46

 nemico

-1.42

⬮

-1.41

and

-1.37

\|_{

-1.36

POSITIVE LOGITS

‘

1.39

ed

1.35

1.34

of

1.33

1.30

si

1.27

 любого

1.24

裏

1.20

 Inverter

1.20

 regler

1.19

Activations Density 0.154%