INDEX

Explanations

foreign words and phrases

The neuron activates on relational or measure words (like “short,” “ago,” “high,” “wide,” “behind,” “after,” “down,” “between,” etc.) that introduce or qualify numeric or quantitative contexts.

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

-1.70

-1.66

and

-1.63

’

-1.55

 because

-1.46

all

-1.45

TWO

-1.45

or

-1.45

by

-1.43

 began

-1.41

POSITIVE LOGITS

emporio

1.63

azienda

1.61

alquiler

1.59

 alkoholu

1.57

 gäng

1.55

 neuesten

1.55

𖣔

1.54

 horrid

1.48

entrevista

1.48

guigu

1.47

Activations Density 0.037%