INDEX

Explanations

sweet or sweets, riches, clippers

The neuron fires on occurrences of the word stem “sweet” (e.g. sweets, sweetie).

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

’

-2.69

\'

-2.63

‘

-2.58

-2.45

was

-2.42

and

-2.34

他又

-2.27

е

-2.08

\_

-2.08

POSITIVE LOGITS

 Mainly

2.83

 When

2.69

 Relatively

2.48

 Technically

2.45

 Equally

2.39

 Sometime

2.34

 Ironically

2.33

 Primarily

2.33

 Somewhat

2.31

橦

2.31

Activations Density 0.001%