INDEX

Explanations

Plus introducing new points

This neuron fires on the additive discourse marker “Plus” when it begins a clause or sentence.

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

and

-1.73

 ControllerBase

-1.23

 primarily

-1.20

についても

-1.18

 především

-1.17

 cependant

-1.17

 simplemente

-1.15

糹

-1.15

but

-1.12

ங

-1.12

POSITIVE LOGITS

 there

1.70

Who

1.63

 siinä

1.43

With

1.37

其他

1.37

There

1.35

 với

1.31

Now

1.31

Once

1.28

Of

1.27

Activations Density 0.010%