INDEX

Explanations

until or before dates and times

The main thing this neuron does is detect numerical tokens (quantities, measurements, or numbers, often with 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

<bos>

-2.00

 zwanzig

-1.55

Isn

-1.49

Wasn

-1.45

 Так

-1.37

 لكن

-1.34

 člá

-1.34

担忧

-1.34

itair

-1.31

The

-1.30

POSITIVE LOGITS

2.25

𖤣

1.39

1.34

'';

1.33

 女の子

1.30

cripción

1.30

 uses

1.29

 δύ

1.26

ズニー

1.26

 such

1.26

Activations Density 0.040%