INDEX

Explanations

peers and colleagues

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

 različ

0.44

 verschied

0.43

 مختلف

0.42

 różne

0.42

}+\

0.39

 अलग

0.38

 verschiedene

0.38

 different

0.38

},

0.38

}\

0.38

POSITIVE LOGITS

 fellow

2.70

 colleagues

2.17

 peers

2.16

 colegas

2.05

fellow

1.98

 compañeros

1.95

 teammates

1.95

Fellow

1.93

 Fellow

1.88

 classmates

1.86

Activations Density 0.029%