INDEX

Explanations

distribution and spreading

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

ور

2.24

ي

2.14

नि

2.06

iant

2.05

er

2.01

_{

2.00

aq

2.00

وف

1.99

Beauty

1.98

ுத

1.97

POSITIVE LOGITS

 wrists

2.60

 ছি

2.38

 rumour

2.37

 dissemination

2.36

 rumor

2.31

 Caen

2.30

 яка

2.30

 frecuencias

2.30

 evenly

2.29

 asignar

2.28

Activations Density 0.269%