INDEX

Explanations

practice of

The neuron fires on words naming or describing the core action or practice in a definitional/explanatory context (e.g. “organisms,” “eliminate,” “practice,” “defecating”).

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

 these

-1.36

 even

-1.26

be

-1.25

 also

-1.19

 then

-1.16

it

-1.13

-1.09

 thus

-1.04

 each

-1.02

 accordingly

-1.02

POSITIVE LOGITS

的一种

1.88

 Projektu

1.46

WillAppear

1.44

Either

1.43

usually

1.35

baliknya

1.34

 sokak

1.34

 Meksi

1.33

łóż

1.28

 genellikle

1.27

Activations Density 0.287%