INDEX

Explanations

warm and affectionate speech

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

 objectionable

0.88

 deleterious

0.85

 prosedur

0.84

 상당히

0.83

 Pareto

0.80

詭

0.80

 necessitating

0.80

 metodologia

0.79

 വിശദ

0.79

 prototypical

0.78

POSITIVE LOGITS

 heartfelt

2.04

 ❤️

1.87

 loving

1.79

 cariño

1.78

 hearts

1.75

❤️

1.73

 hugs

1.68

 heartwarming

1.67

 friendship

1.66

 cuddle

1.65

Activations Density 1.108%