INDEX

Explanations

describes, notes

The neuron detects scholarly attribution or reporting cues—words like “describes,” “reports,” “notes,” “reviews,” etc., that signal a citation or reference.

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

 your

-1.08

ustomed

-1.05

 '/';

-1.02

 irgende

-1.01

嚕

-1.00

 cauza

-0.99

/>

-0.97

 deinem

-0.97

мання

-0.96

POSITIVE LOGITS

in

1.45

 this

1.39

 these

1.31

for

1.23

 that

1.10

 even

1.06

how

1.04

“

1.03

 three

1.02

 cortinas

1.00

Activations Density 0.030%