INDEX

Explanations

return value

The neuron fires on C/C++ pointer‐member access (the “->” operator).

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

↵↵

-1.67

you

-1.63

 When

-1.45

 pretože

-1.28

 Just

-1.27

 improves

-1.27

ทำให้

-1.25

 Like

-1.25

How

-1.24

by

-1.23

POSITIVE LOGITS

᯾

2.03

‘

1.88

۷

1.59

𖧵

1.56

‚

1.56

=’

1.56

”;

1.55

 игрушки

1.54

&#

1.53

and

1.52

Activations Density 0.001%