INDEX

Explanations

is followed by description

The neuron fires on instances of process‐describing verbs in passive constructions—especially forms of “to be” (e.g. “is performed,” “is executed,” “is induced”) signaling scientific or procedural statements.

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

'#'

-1.54

 "}";

-1.53

 fread

-1.52

 terrasse

-1.51

 canadensis

-1.48

 brillant

-1.48

 должен

-1.47

 ""],

-1.46

 должна

-1.45

'('

-1.44

POSITIVE LOGITS

𝗮

1.98

↵

1.77

 beendet

1.76

 beschränkt

1.72

 geschieht

1.70

 done

1.70

 processes

1.66

⁫

1.65

合作伙伴

1.61

 Other

1.60

Activations Density 0.195%