INDEX

Explanations

Enron Corp

This neuron selectively fires on capitalized proper nouns referring to “East”/“Eastern” and the company name token “Enron.”

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

錚

-1.62

してました

-1.61

ﾄ

-1.50

sprzed

-1.47

ご利用

-1.47

and

-1.46

 isnt

-1.45

 selecting

-1.44

 handing

-1.42

เพราะ

-1.42

POSITIVE LOGITS

THERE

1.86

 anunció

1.79

didn

1.77

 .........

1.71

-(

1.71

 .......

1.70

 …..

1.68

originally

1.63

</h3>

1.63

-.

1.62

Activations Density 0.022%