INDEX

Explanations

sincere, genuine, or warm closings and expressions

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

 scary

0.89

 miraculously

0.82

 taboo

0.79

嗥

0.76

 morph

0.74

 handy

0.74

 replies

0.73

 magically

0.71

 creepy

0.71

 tantrums

0.69

POSITIVE LOGITS

 sincere

1.70

 sincer

1.49

 genuine

1.38

 sinc

1.33

 Genuine

1.31

 sincerity

1.29

 иск

1.24

깊

1.24

genuine

1.24

 warmest

1.22

Activations Density 0.140%