INDEX

Explanations

go or come followed by action

The neuron fires on second-person imperative action words (e.g. “go,” “come”) directing the reader to do something.

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

 that

-2.11

on

-1.90

 hingga

-1.71

 många

-1.54

 many

-1.49

 resurrection

-1.46

 memakai

-1.44

-1.41

gdy

-1.41

indest

-1.40

POSITIVE LOGITS

Отзывы

1.75

 报告

1.56

 μόνο

1.56

 territ

1.53

ၞ

1.52

ONLY

1.50

 hispan

1.48

 domina

1.46

だけ

1.41

Empereur

1.41

Activations Density 0.015%