INDEX

Explanations

dimensions, dimensionality, dimension

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

謁

-0.80

رامج

-0.74

ряд

-0.74

nictwa

-0.73

 erreichte

-0.73

 מאוד

-0.68

唔係

-0.66

六月

-0.66

duur

-0.65

тельства

-0.65

POSITIVE LOGITS

 dimension

3.45

 dimensionality

3.08

 dimensions

2.83

dimension

2.73

Dimension

2.61

 Dimension

2.59

dimensions

2.30

 Dimensions

2.16

 dimensión

2.14

 dimen

2.09

Activations Density 0.076%