INDEX

Explanations

for example, for instance, inter alia

The main thing this neuron does is detect phrases that introduce examples or elaborations (e.g. “for example,” “for instance,” “inter alia”).

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

and

-2.03

-1.83

But

-1.66

Награды

-1.66

 belki

-1.65

 this

-1.64

 However

-1.64

 clogged

-1.60

OF

-1.59

作って

-1.55

POSITIVE LOGITS

“

2.34

You

1.98

—“

1.97

1.94

</h3>

1.91

-“

1.90

de

1.88

,“

1.84

which

1.83

 čtyř

1.75

Activations Density 0.006%