INDEX

Explanations

int declarations in source code

The neuron fires on primitive numeric type tokens (e.g. “int”, “double”) in the code.

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

,”

-1.95

ández

-1.72

óch

-1.69

王爷

-1.63

isição

-1.63

 fournisseurs

-1.57

 fichiers

-1.54

 Arhi

-1.53

公式サイト

-1.52

 techniczne

-1.52

POSITIVE LOGITS

(!__

2.17

</h3>

1.90

 аналоги

1.81

 porém

1.77

鈑

1.77

焄

1.76

 แต่

1.74

 sostu

1.71

 amenaz

1.70

';

1.70

Activations Density 0.005%