INDEX

Explanations

seeing yourself or ourselves

The neuron detects reflexive self-references—words like “myself,” “yourself,” or “ourselves.”

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

 vierge

-1.59

 câmera

-1.51

 vantagem

-1.50

 lienzo

-1.49

 confuso

-1.48

 arquitetura

-1.48

<bos>

-1.48

футболка

-1.45

utado

-1.43

ýchod

-1.41

POSITIVE LOGITS

 while

1.67

to

1.60

 instead

1.47

 during

1.47

 with

1.41

 mientras

1.38

Indeed

1.35

Also

1.33

like

1.32

 that

1.30

Activations Density 0.110%