INDEX

Explanations

from person to person

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

or

1.09

 Drugs

1.01

 malware

1.00

 malignant

0.96

 nags

0.94

 things

0.94

 criminals

0.94

 indicated

0.93

and

0.92

 chast

0.92

POSITIVE LOGITS

velopp

1.06

első

1.03

học

1.01

 అభివృద్ధి

1.01

Très

1.01

 câteva

1.00

τική

0.99

ských

0.99

 šte

0.99

Основные

0.97

Activations Density 0.005%