INDEX

Explanations

Let. Calculate. If. What

The neuron fires on standalone declarative sentences—especially ones stating a definition or concise answer (e.g. “G is a multiplicative group of prime order p.”).

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

 Both

-3.20

-2.91

檮

-2.30

.......

-2.27

....

-2.25

 hacer

-2.22

-2.20

At

-2.19

is

-2.19

 What

-2.11

POSITIVE LOGITS

粜

2.86

GillaGilla

2.58

蠓

2.56

葙

2.55

⾞

2.52

âtel

2.48

Hmmm

2.48

 отличаются

2.47

蠲

2.41

⁛

2.41

Activations Density 0.151%