INDEX

Explanations

sequence of consequences

The neuron strongly activates on numeric tokens (integers or decimals), i.e. occurrences of numbers or measurements in the text.

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

 Also

-1.51

 azonban

-1.33

 manteiga

-1.29

 ainsi

-1.27

 그리고

-1.24

}}+

-1.23

%,

-1.19

 inoltre

-1.18

でしたが

-1.17

 zudem

-1.16

POSITIVE LOGITS

 will

1.48

的问道

1.36

 continúas

1.27

the

1.27

 allerlei

1.23

 chilena

1.20

 Majesté

1.19

 zamiast

1.19

 peruana

1.17

那些

1.16

Activations Density 0.026%