INDEX

Explanations

density of states

The neuron is specialized to pick out multiword “[noun] of [noun]” phrases (e.g. “density of states,” “equation of motion,” “loss of function”).

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

This

-2.11

If

-2.02

How

-1.95

You

-1.93

what

-1.91

When

-1.89

Surprisingly

-1.84

It

-1.81

two

-1.76

Where

-1.76

POSITIVE LOGITS

 également

2.00

珝

1.88

 ก็

1.87

灩

1.87

也

1.84

étés

1.83

いただきたい

1.82

OCOLATE

1.81

 również

1.79

淬

1.78

Activations Density 0.113%