INDEX

Explanations

numbers after specific tokens

The neuron fires on standalone numeric tokens (digit sequences, including integers and decimals) whenever they appear in the text.

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

()));

-1.43

%);

-1.40



-1.38

armani

-1.38

%;

-1.37

\}$.

-1.33

𝔸

-1.33

$~

-1.31

actively

-1.31

%).

-1.31

POSITIVE LOGITS

1.88

1.76

</strong>

1.52

we

1.41

our

1.38

Something

1.37

Our

1.36

Many

1.35

 võib

1.35

 Another

1.33

Activations Density 0.003%