INDEX

Explanations

actions verb past tense

The main thing this neuron does is detect numeric values and quantitative measurements (e.g., numbers, percentages, and statistical figures).

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

-1.90

 mépris

-1.55

 gosta

-1.41

to

-1.34

青木

-1.33

悩む

-1.32

和風

-1.32

 interessantes

-1.31

It

-1.28

veira

-1.27

POSITIVE LOGITS

 that

2.70

if

1.83

 любого

1.47

рных

1.40

 pemandangan

1.40

or

1.36

有任何

1.36

 cercano

1.33

⇐

1.30

erializer

1.29

Activations Density 0.123%