INDEX

Explanations

lists

This neuron specializes in detecting detailed technical or engineering descriptions of mechanical processes (e.g., how an aircraft turbine engine operates).

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

it

-1.89

 from

-1.56

It

-1.35

 fueran

-1.28

 denselben

-1.22

baomidou

-1.21

}));

-1.20

:'',

-1.19

.*;

-1.19

Т

-1.19

POSITIVE LOGITS

的她

1.27

قرير

1.26

 rire

1.23

畫

1.20

 ngunit

1.17

Namun

1.16

 tonel

1.15

髙

1.15

のですが

1.13

raciones

1.13

Activations Density 0.724%