INDEX

Explanations

programming language keywords

The neuron activates on occurrences of method or function names (e.g. “concat,” “count,” “include?”) in 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

 have

-1.90

was

-1.85

 create

-1.34

在其

-1.34

выми

-1.34

錸

-1.31

 conector

-1.31

同様に

-1.30

色は

-1.29

 настолько

-1.28

POSITIVE LOGITS

おわりに

1.57

 This

1.54

 Nuestro

1.50

even

1.50

 данной

1.48

 Siempre

1.47

媗

1.47

this

1.47

ざ

1.44

what

1.43

Activations Density 0.004%