INDEX

Explanations

days and weeks

This neuron detects date and time references, such as months, weekdays, and numeric day/month values.

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

for

-1.78

 about

-1.59

 better

-1.54

 more

-1.53

fua

-1.48

 would

-1.44

 tramont

-1.36

 will

-1.35

 drau

-1.34

phylaxis

-1.34

POSITIVE LOGITS

but

1.36

or

1.36

1.27

又は

1.23

 или

1.23

 وَ

1.22

徒歩

1.20

«

1.20

 из

1.20

期间

1.16

Activations Density 0.093%