INDEX

Explanations

the followed by a subject

The neuron activates on numeric tokens (e.g. numbers, percentages, decimal values).

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

 when

-1.78

});

-1.73

🤣🤣

-1.67

🥲

-1.65

٧

-1.65

vamo

-1.57

ised

-1.53

٨

-1.52

%;">

-1.52

if

-1.49

POSITIVE LOGITS

of

2.16

 increasingly

1.48

 такого

1.48

此事

1.41

 começaram

1.38

 pensamento

1.35

 этого

1.34

 this

1.32

このように

1.31

がこの

1.30

Activations Density 0.094%