INDEX

Explanations

joining elements in code

This neuron detects occurrences of the array `.join(` method call (i.e. “.join(”) 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

to

-2.73

in

-2.38

and

-2.20

一秒

-1.72

The

-1.60

\\

-1.59

 zelfs

-1.59

⩕

-1.59

vertebrates

-1.59

跺

-1.57

POSITIVE LOGITS

というわけで

1.77

 اوم

1.70

灕

1.67

所謂

1.62

 Especially

1.60

pherds

1.59

うーん

1.56

 Pièces

1.56

 habitudes

1.56

比如说

1.55

Activations Density 0.003%