INDEX

Explanations

the city of Paris

attends to specific token identifiers of people or entities in a historical context from general or descriptive tokens.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

Negative Logits

 resourceCulture

-0.85

colleg

-0.63

Toma

-0.63

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

-0.62

glUniform

-0.62

}`).

-0.62

чее

-0.62

BufferException

-0.61

⁩

-0.61

伴

-0.60

POSITIVE LOGITS

 Paris

1.26

Paris

1.17

 PARIS

1.13

paris

1.05

PARIS

1.02

 paris

0.93

 ISIS

0.84

 París

0.80

 Parisi

0.80

Kelas

0.77

Activations Density 0.002%