INDEX

Explanations

problems or things not working

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

 riesgos

0.97

 stanowi

0.92

 doskona

0.88

 bowiem

0.87

 கற்ப

0.86

 위한

0.86

 risques

0.86

 promulg

0.86

 destiné

0.86

 oeuvre

0.85

POSITIVE LOGITS

 strange

1.42

 inexplicable

1.37

 weird

1.31

 inexplic

1.23

奇怪

1.21

 sudden

1.17

 unexplained

1.15

 strangely

1.14

strange

1.14

odd

1.12

Activations Density 0.451%