INDEX

Explanations

mentions of numerical comparisons, especially percentages, ratios, and "times"

doubling

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

Negative Logits

RegressionTest

-0.70

IntoConstraints

-0.69

MigrationBuilder

-0.66

qrstuvwxyz

-0.65

########.

-0.65

 estekak

-0.65

AutoField

-0.64

 للاسماء

-0.60

 الحره

-0.60

 kasarigan

-0.60

POSITIVE LOGITS

 twice

2.00

 double

1.90

 Twice

1.73

twice

1.72

double

1.71

Twice

1.66

 DOUBLE

1.45

 Double

1.45

 doble

1.45

DOUBLE

1.41

Activations Density 2.026%