INDEX

Explanations

conditional statements or requirements

The neuron primarily responds to English modal verbs (like “must,” “should,” “can”) that signal obligation or permission.

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

 preponder

-1.00

₨

-0.92

 indes

-0.88

感受

-0.87

INFIN

-0.86

 preval

-0.85

 preced

-0.83

 डि

-0.80

MÁS

-0.80

ου

-0.80

POSITIVE LOGITS

any

1.52

 unless

1.42

 either

1.40

if

1.39

 cannot

1.39

 otherwise

1.37

so

1.34

 must

1.29

 other

1.26

 exception

1.25

Activations Density 0.060%