INDEX

Explanations

technical prepositions and common examples

This neuron detects text that introduces formal data‐structure or schema definitions (e.g. phrases like “following” and the “:-” marker in a table/structure declaration).

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

 this

-1.33

 with

-1.31

 diperhatikan

-1.30

 allows

-1.27

When

-1.27

 gives

-1.27

※

-1.27

 mainly

-1.26

People

-1.24

 greatly

-1.22

POSITIVE LOGITS

unn

1.68

 alluring

1.28

 remedi

1.28

 insanely

1.27

 magnificent

1.27

 Beide

1.27

 ambigu

1.27

 absurd

1.27

 lauded

1.27

 serene

1.24

Activations Density 0.243%