INDEX

Explanations

introducing a reason or explanation

The neuron fires on common English function words—especially the pronoun “it,” the copula “is,” the negator “not,” and the conjunction “because.”

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

-1.19

หน่อย

-1.17

 also

-1.14

 Bored

-1.03

notEmpty

-0.95

[])

-0.93

 Ignoring

-0.92

 helps

-0.89

 particularly

-0.87

 Proceeding

-0.85

POSITIVE LOGITS

it

2.00

而是

1.87

nor

1.80

 they

1.69

 sondern

1.57

nor

1.39

 there

1.38

 слишком

1.28

 unless

1.27

 terlalu

1.24

Activations Density 0.039%