INDEX

Explanations

not just

The neuron strongly responds to the adverb “just” (and similar emphatic/discourse-marker uses of “just”) in sentences.

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

WHY

-1.86

 DIDN

-1.78

 couverte

-1.76

 medlem

-1.68

iwisata

-1.66

 большинстве

-1.62

 WHILE

-1.60

 WOULD

-1.57

 étan

-1.56

 équipée

-1.56

POSITIVE LOGITS

for

2.34

1.72

and

1.66

 will

1.66

 when

1.63

 pushes

1.55

 offers

1.54

For

1.52

 people

1.52

Also

1.50

Activations Density 0.021%