INDEX

Explanations

ordinal of quantity or group

The neuron strongly activates on the word “of.”

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

 estekak

-1.88

and

-1.77

,:)

-1.75

——”

-1.75

𓆜

-1.70

oczes

-1.67

thirsty

-1.63

poons

-1.63

 there

-1.59

mados

-1.59

POSITIVE LOGITS

 willen

1.63

1.62

 those

1.57

也不

1.49

 تقری

1.47

Of

1.45

うわ

1.42

也

1.41

1.37

lossians

1.34

Activations Density 0.060%