INDEX

Explanations

emojis and specific code/word structures

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

 средства

1.20

wars

1.18

ించే

1.16

 Emperors

1.15

 starost

1.14

اعری

1.13

ларын

1.13

 étant

1.12

 súčas

1.12

+}$

1.12

POSITIVE LOGITS

️

1.37

੫

1.24

куси

1.22

 permeates

1.12

1.11

 ग्रस्त

1.10

el

1.09

燉

1.07

ek

1.04

 separates

1.04

Activations Density 0.009%