INDEX

Explanations

points out that

The neuron fires on the subordinating conjunction “that” when it introduces a reported or asserted clause (e.g. in “points out that,” “notes that,” “noted that,” “reports that”).

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

and

-1.70

or

-1.55

at

-1.45

 give

-1.35

as

-1.34

 from

-1.32

 will

-1.32

 believes

-1.28

on

-1.27

 over

-1.21

POSITIVE LOGITS

 przecież

1.61

unlike

1.47

 pronon

1.46

quickly

1.42

previously

1.41

 recente

1.40

albeit

1.37

despite

1.37

 apropri

1.35

several

1.34

Activations Density 0.010%