INDEX

Explanations

articles preceding nouns

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

something

1.34

 something

1.31

Something

1.27

 شيء

1.25

 Something

1.24

 อะไร

1.21

 coś

1.20

what

1.19

뭐

1.19

 someth

1.18

POSITIVE LOGITS

 selected

1.39

 specified

1.18

selected

1.16

 several

1.08

 five

1.05

 three

1.04

six

1.02

 various

1.01

 select

1.00

 Selected

1.00

Activations Density 0.507%