INDEX

Explanations

reports followed by a colon

The neuron detects tokens that introduce or point to external references or navigation cues—bylines, hyperlinks, or “read more”-type pointers (e.g. “via,” “reports,” colons, “below,” “more info,” etc.).

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

 then

-1.59

but

-1.43

 somewhat

-1.41

not

-1.39

if

-1.38

 большин

-1.38

 платье

-1.29

duk

-1.26

 later

-1.25

no

-1.24

POSITIVE LOGITS

1.55

 with

1.55

 from

1.49

on

1.36

</strong>

1.32

 tilgjenge

1.20

gjenge

1.20

ம

1.16

 alebo

1.14

الغ

1.13

Activations Density 0.028%