INDEX

Explanations

prepositional phrases and common verbs

The neuron fires on words that signal procedural or logical relations—e.g. conditionals and action cues like “if,” “for,” “use,” “post,” “moves,” 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

 adatok

-1.38

styp

-1.37

ícias

-1.37

 familien

-1.33

Scrollable

-1.31

TOWN

-1.29

 هذا

-1.29

 คน

-1.26

 metrów

-1.25

鲥

-1.25

POSITIVE LOGITS

 what

2.08

 their

1.62

any

1.55

 aforementioned

1.45

ヵ

1.43

 making

1.39

。』

1.38

 meantime

1.38

it

1.37

1.36

Activations Density 0.179%