INDEX

Explanations

asking for assistance or suggestions

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

 crappy

1.42

 yelled

1.32

 wacky

1.25

 goofy

1.23

 sneaky

1.23

 yelling

1.21

 haters

1.20

 mamá

1.17

 whopping

1.16

 fake

1.16

POSITIVE LOGITS

 circumstances

1.21

 perhaps

1.10

 прошу

1.03

 consideration

1.02

perhaps

1.01

 ascertain

1.00

どのような

1.00

 весьма

1.00

 अथवा

0.99

 осуществля

0.99

Activations Density 0.179%