INDEX

Explanations

rising or growing numbers

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 numbering

-1.08

 küm

-0.84

 Follows

-0.81

 хок

-0.80

ває

-0.80

 Brace

-0.77

también

-0.75

=["

-0.75

ಒ

-0.74

醐

-0.74

POSITIVE LOGITS

 rising

3.08

 rises

2.47

 rise

2.41

rising

2.36

 rose

2.16

Rising

2.05

 Rising

2.02

 increasing

1.91

 risen

1.91

 climbing

1.84

Activations Density 0.070%