INDEX

Explanations

introducing lists or summaries

The neuron is effectively inactive (it does not reliably activate on any particular token or pattern).

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

-1.95

ING

-1.55

TestingModule

-1.38

達が

-1.37

 Substanz

-1.37

 equals

-1.36

It

-1.32

人數

-1.31

に乗って

-1.31

POSITIVE LOGITS

of

2.23

 example

1.79

畦

1.77

now

1.60

 list

1.59

 dalších

1.47

 сейчас

1.47

τής

1.47

=='

1.42

Chore

1.41

Activations Density 0.128%