INDEX

Explanations

numbers and foreign words

The neuron activates on standalone numeric values (e.g. integers or decimals).

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

 after

-1.64

 españolas

-1.45

borderSide

-1.43

 urbanas

-1.42

</h2>

-1.42

….”

-1.41

支払

-1.40

 cercanas

-1.35

 this

-1.34

Ży

-1.31

POSITIVE LOGITS

1.51

 discut

1.42

有两

1.36

 huit

1.35

渽

1.34

 حت

1.33

两

1.29

 whether

1.28

 venga

1.25

 zweier

1.23

Activations Density 0.019%