INDEX

Explanations

recurring actions

This neuron detects the phrase “each time,” marking repeated occurrences or iterations.

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

 Consejos

-1.45

 sayap

-1.42

 هؤلاء

-1.39

ڨ

-1.38

-1.37

इटम

-1.36

 całą

-1.35

ACIONAL

-1.34

 zijne

-1.32

众多

-1.32

POSITIVE LOGITS

 разные

1.70

of

1.69

om

1.52

as

1.48

lo

1.38

like

1.34

in

1.34

 ſou

1.34

and

1.33

 mentre

1.33

Activations Density 0.013%