INDEX

Explanations

categorized possibilities and preferences

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

specific

1.14

 specific

1.09

Specific

1.03

 Specific

0.99

 конкре

0.99

 específica

0.98

 específico

0.97

 konkrét

0.93

 específicamente

0.90

具体

0.88

POSITIVE LOGITS

 preferences

1.92

 Preferences

1.91

 preference

1.76

 preferencias

1.72

 prefer

1.66

 Preference

1.66

 preferencia

1.61

 prefers

1.59

 preferred

1.59

preferences

1.55

Activations Density 0.678%