INDEX

Explanations

such a, such that

The neuron fires on words that serve as general-purpose qualifiers, quantifiers, or intensifiers (e.g. “such,” “any,” “enough,” “poor,” “whole,” “after,” “that,” “not,” etc.).

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

it

-1.74

 there

-1.65

opportunities

-1.46

 potes

-1.42

 time

-1.41

先日

-1.39

＊＊＊＊

-1.38

 that

-1.38

 respira

-1.37

 this

-1.36

POSITIVE LOGITS

 gemens

1.43

 alltså

1.29

 nästan

1.27

for

1.27

 azok

1.24

 olyan

1.24

就不能

1.23

 MANY

1.22

 zusätzlichen

1.21

Activations Density 0.096%