INDEX

Explanations

the neuron is looking for URLs and online web addresses.

The neuron is keyed to detecting web addresses (e.g. the “www” token in URLs).

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

ч

0.42

ра

0.40

пи

0.39

一百

0.38

тся

0.36

 muest

0.36

か

0.36

ត្

0.35

 perhitungan

0.35

сы

0.34

POSITIVE LOGITS

<0x0D>

0.47

0.43

0.40

for

0.39

iro

0.39

 during

0.39

ing

0.38

by

0.36

at

0.36

nyder

0.35

Activations Density 0.001%