INDEX

Explanations

foreign language words

The neuron detects section headings (e.g. “Distribution,” “Systematics,” “References,” “Hosts,” etc.) in a structured document.

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

for

-1.60

 also

-1.52

jados

-1.49

Then

-1.44

astă

-1.38

早速

-1.34

Quien

-1.32

さっそく

-1.30

Viernes

-1.29

 than

-1.28

POSITIVE LOGITS

1.33

/*!

1.26

either

1.26

1.23

않

1.21

ATHER

1.20

↵

1.18

icznego

1.18

 molti

1.16

Activations Density 0.064%