INDEX

Explanations

references to specific similarity terms or phrases

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

No Comments

Negative Logits

Likewise

-0.91

 Likewise

-0.84

 Similarly

-0.64

 likewise

-0.61

 equally

-0.60

 similarly

-0.59

Similarly

-0.54

Choisissez

-0.53

 fraction

-0.51

amela

-0.51

POSITIVE LOGITS

Similar

2.00

 Similar

1.61

principalTable

0.93

Datuak

0.84

 semej

0.81

 MainAxisSize

0.75

__':

0.73

henswürdigkeiten

0.70

__":

0.67

detectChanges

0.67

Activations Density 0.002%