INDEX

Explanations

what does it mean

The neuron is looking for usages of “mean” in questions asking “what does … mean?”—i.e. definition‐seeking contexts.

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

of

-3.09

the

-2.52

for

-2.02

in

-1.84

to

-1.63

-1.50

as

-1.48

to

-1.47

als

-1.47

for

-1.45

POSITIVE LOGITS

Cartney

1.66

umą

1.55

 that

1.53

 DOMINGO

1.53

 elettrica

1.52

Etimología

1.51

珝

1.48

 绘画

1.47

timmt

1.46

 appartenant

1.45

Activations Density 0.276%