INDEX

Explanations

numbers and symbols in formulas

The neuron is specialized in detecting numeric tokens, especially floating‐point numbers (decimal measurements) 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

ᥬ

-1.84

 зді

-1.77

});

-1.61

ające

-1.56

的金

-1.55

Więcej

-1.52

');

-1.49

 शुर

-1.46

 anlam

-1.46

 Another

-1.45

POSITIVE LOGITS

1.83

 haupts

1.80

 that

1.73

人には

1.52

 their

1.52

使って

1.44

 schli

1.42

你就

1.42

 verbessern

1.41

就可以

1.40

Activations Density 0.015%