INDEX

Explanations

originally planned or intended

The neuron activates on words and phrases that signal an original plan or initial intention—e.g. “initially,” “originally,” “planned to,” and similar.

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

is

-1.32

भाव

-1.17

نجليز

-1.14

已经

-1.12

já

-1.12

itzen

-1.11

\{

-1.08

inning

-1.08

 כבר

-1.08

 lámparas

-1.07

POSITIVE LOGITS

 only

1.76

 about

1.59

Your

1.42

 even

1.32

 this

1.27

 sexto

1.23

oires

1.22

emotional

1.20

</h5>

1.17

 лишь

1.16

Activations Density 0.041%