INDEX

Explanations

this

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ourselves

-1.09

我們的

-0.69

Our

-0.68

Geplaatst

-0.67

我们将

-0.66

 avem

-0.66

Our

-0.65

premiere

-0.65

私たちは

-0.64

 máme

-0.64

POSITIVE LOGITS

to

0.63

as

0.57

 sich

0.54

prepareStatement

0.51

the

0.50

 magát

0.50

 themselves

0.48

.“

0.48

tiéndose

0.48

Activations Density 0.257%