INDEX

Explanations

will be; will + verb

The neuron primarily detects the modal auxiliary “will,” marking future‐tense constructions.

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

-1.59

 puis

-1.34

 ridd

-1.34

 parfois

-1.33

beca

-1.28

GIVE

-1.28

भु

-1.28

zon

-1.27

 płasz

-1.26

 THOUS

-1.25

POSITIVE LOGITS

two

1.74

 three

1.60

and

1.58

 from

1.55

Two

1.55

had

1.55

Two

1.54

 Several

1.49

 with

1.46

 will

1.45

Activations Density 0.057%