INDEX

Explanations

Romanization and numerals

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 وهذه

2.05

м

2.03

 moul

1.98

 reduc

1.89

 وعلى

1.87

قه

1.86

 vive

1.85

cui

1.82

 proteg

1.79

ために

1.76

POSITIVE LOGITS

קה

2.03

 appellants

1.99

ly

1.96

রাও

1.95

 anodes

1.94

ojn

1.93

рани

1.91

ਂ

1.91

")}}

1.90

 VESSELS

1.90

Activations Density 0.009%