INDEX

Explanations

sequences A, B, C

The neuron activates on tokens representing decimal numbers (numerical values containing a decimal 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

 innymi

-1.48



-1.39

taminophen

-1.37

 weitgehend

-1.34

 arrêté

-1.34

medriver

-1.31

褛

-1.30

 kontinuier

-1.26

 valioso

-1.26

 potra

-1.24

POSITIVE LOGITS

–

1.83



1.58

1.55

1.45

 вопросы

1.36

It

1.35

»,

1.34

//}

1.32

нима

1.30

Activations Density 0.081%