INDEX

Explanations

the noun

The neuron predominantly activates on occurrences of the definite article “the.”

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

 ſuch

-1.59

 moſt

-1.56

sements

-1.53

讷

-1.52

และ

-1.49

 alluring

-1.45

 autorité

-1.44

𝐒

-1.44

mentaux

-1.41

<0xE1>

-1.41

POSITIVE LOGITS

↵

2.64

1.96

地说

1.61

 каждый

1.57

1.55

 chcesz

1.52

ですが

1.52

1.48

 first

1.48

他自己

1.43

Activations Density 0.430%