INDEX

Explanations

another + introductory noun phrase

This neuron responds to the discourse marker “another,” i.e. occurrences of the word “another” signaling an additional example or point.

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

who

-1.81

 wasn

-1.58

 wouldn

-1.55

 couldn

-1.46

 didn

-1.45

わけではない

-1.31

 brasile

-1.30

ército

-1.27

 after

-1.26

说的

-1.24

POSITIVE LOGITS

}$.

1.46

."

1.45

 church

1.43

 bagus

1.38

كويكب

1.35

 chúng

1.29

 handful

1.29

 ailleurs

1.28

 میلیارد

1.27

 workforce

1.23

Activations Density 0.038%