INDEX

Explanations

well followed by comma or certain words

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

ي

2.75

2.50

et

2.44

2.41

يها

2.27

ação

2.19

daki

2.03

২১

1.98

1.96

ת

1.94

POSITIVE LOGITS

ğini

2.00

 hijacked

1.95

 adanya

1.92

 όχι

1.86

 gonorrhea

1.84

 anschließend

1.83

覀

1.83

ன்

1.82

 versed

1.82

ierung

1.79

Activations Density 0.066%