INDEX

Explanations

times and dates

This neuron detects numeric tokens—especially digits and punctuation used in timestamps or time expressions.

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

’)

-1.88

’:

-1.86

”،

-1.81

 melalui

-1.77

nor

-1.76

</u>

-1.71

໊

-1.68

嫱

-1.67

 zwei

-1.67

’.

-1.63

POSITIVE LOGITS

1.55

惲

1.52

rasında

1.52

過ぎ

1.47

 rejuven

1.46

section

1.45

 They

1.45

座位

1.43

之为

1.41

馀

1.41

Activations Density 0.009%