INDEX

Explanations

citing examples or references

This neuron activates on in-text reference citations (e.g. the “See, <number> for example,” style pointers to prior art).

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

-2.06

Its

-1.89

“

-1.88

姈

-1.64

 その

-1.52

</b>

-1.52

 которую

-1.52

 которое

-1.50

-1.48

のですが

-1.45

POSITIVE LOGITS

and

2.20

 动漫

1.75

瞜

1.71

idr

1.62

 territo

1.62

 alha

1.55

摃

1.52

 kela

1.52

 lemp

1.52

 were

1.51

Activations Density 0.006%