INDEX

Explanations

quantities and units

The neuron detects numeric measurement expressions, especially quantities with units (e.g. “ounce,” “grams,” “g”).

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

᭝

-1.68

 språk

-1.66

تیجه

-1.66

juc

-1.56

禤

-1.54

 problemen

-1.53

镂

-1.51

pography

-1.49

⚣

-1.45

 исключительно

-1.45

POSITIVE LOGITS

,"

2.02

1.81

of

1.73

1.58

1.54

眼下

1.40

 aconse

1.38

 recopila

1.38

 enfati

1.37

 achten

1.34

Activations Density 0.009%