INDEX

Explanations

patterns and 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

 лет

1.27

 activa

1.23

 oczy

1.19

 maî

1.18

 ovulation

1.16

 vigilancia

1.12

<unused235>

1.12

ព្យ

1.11

<unused2116>

1.10

 paisajes

1.10

POSITIVE LOGITS

et

1.24

duğ

1.20

𝐀

1.05

odigd

1.04

𝘢

1.03

सँग

1.03

duğu

1.01

ein

1.01

यर

1.01

ной

1.00

Activations Density 0.007%