INDEX

Explanations

foreign words and punctuation

The neuron activates on numeric tokens (especially decimal numbers) representing measurements or statistical values.

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

']."

-1.34

'=>'

-1.30

她们

-1.30

 mereka

-1.29

他们

-1.24

or

-1.23

'=>$

-1.17

dzić

-1.16

},

-1.13

مقاله

-1.13

POSITIVE LOGITS

 selalu

1.38

in

1.35

 speziellen

1.30

 grossen

1.27

 najlep

1.22

butuhkan

1.21

 Nuevas

1.20

 zawsze

1.19

 partea

1.19

 reaffirm

1.17

Activations Density 0.577%