INDEX

Explanations

words either preceded or followed by a parenthesis

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

 raiſ

-0.82

 myſelf

-0.81

 houſe

-0.74

Efq

-0.73

 Theſe

-0.71

 whoſe

-0.71

 itſelf

-0.71

 Shakspeare

-0.69

 ſhe

-0.68

 becauſe

-0.67

POSITIVE LOGITS

الإنجليزية

0.70

utnik

0.68

/*---

0.67

Portale

0.62

)!=

0.61

writeFieldEnd

0.61

SPATH

0.60

[]:

0.60

DropTable

0.60

medriver

0.59

Activations Density 0.016%