INDEX

Explanations

x and y coordinates

The neuron fires on occurrences of “x” (or “X”) when it appears as a variable or parameter name, especially in code contexts for x-coordinates or related dimensions.

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

↵↵↵↵

-1.47

-1.34

-1.31

-1.30

↵↵↵

-1.29

la

-1.24

to

-1.23

you

-1.20

POSITIVE LOGITS

and

1.43

 escuchado

1.38

 projekty

1.31

voyez

1.27

 geïsole

1.20

 jednod

1.19

ração

1.17

mässig

1.17

侥

1.15

 geluid

1.14

Activations Density 0.021%