INDEX

Explanations

"the" or "this" followed by a noun

The neuron detects sentence boundaries, firing strongly on sentence-final punctuation (periods) and the first word of a new sentence.

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

璈

-1.37

 pesa

-1.34

</blockquote>

-1.33

邶

-1.32

︲

-1.28

嫒

-1.23

蕓

-1.23

榇

-1.22

 gerai

-1.20

 perfeito

-1.19

POSITIVE LOGITS

 they

1.55

mètres

1.38

or

1.34

斃

1.31

ympto

1.28

 indigestion

1.27

塬

1.25

 Jeśli

1.24

ằm

1.23

場合があります

1.23

Activations Density 0.024%