INDEX

Explanations

linking words and phrases

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

 amma

2.01

ouncement

1.90

&/

1.87

 organisers

1.85

’

1.83

 historians

1.81

1.75

 lược

1.72

&-

1.72

сле

1.72

POSITIVE LOGITS

as

2.79

rinsic

2.55

 као

2.55

 sebagai

2.51

 como

2.48

 як

2.44

kao

2.34

2.18

 comme

2.16

как

2.15

Activations Density 0.646%