INDEX

Explanations

"when" followed by conditions

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

 dàng

2.62

}$\

2.27

žil

2.09

祉

2.01

}$)

1.98

 путь

1.97

ם

1.97

owane

1.93

}$=

1.91

ટ

1.88

POSITIVE LOGITS

 faced

3.52

 जेव्हा

2.96

หร่

2.74

 confronted

2.71

마다

2.71

либо

2.64

र्द

2.57

दस्त

2.56

soever

2.53

2.46

Activations Density 0.114%