INDEX

Explanations

company actions and beliefs

This neuron detects first-person plural references (e.g., “we,” “our”) used in corporate or service descriptions.

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

 naszego

-1.79

咎

-1.67

 Características

-1.66

 dotyczące

-1.56

ěř

-1.54

 decorativos

-1.53

 Terkait

-1.52

 nowych

-1.52

？】

-1.52

estaba

-1.52

POSITIVE LOGITS

↵↵

1.84

 also

1.54

and

1.46

th

1.43

un

1.37

ate

1.34

1.32

龊

1.31

</td>

1.31

</i>

1.30

Activations Density 0.045%