INDEX

Explanations

gratitude and negative sentiment

abstract nouns denoting general states, processes, or measurable quantities.

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

раб

1.86

 Defaults

1.82

พันธุ์

1.78

୯

1.71

 пала

1.70

iguity

1.69

 Peer

1.67

 الأ

1.66

 جامعة

1.66

 مُ

1.65

POSITIVE LOGITS

いただき

1.55

到了

1.49

 Donc

1.46

erequisites

1.45

scor

1.45

okkaido

1.43

xcor

1.43

 insides

1.42

 lạnh

1.41

 οποίο

1.41

Activations Density 0.000%