INDEX

Explanations

concocted, deducted, ducted

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

ق

1.56

ى

1.32

قية

1.31

ভাষায়

1.30

.}$

1.30

1.22

ק

1.20

gp

1.17

 אתה

1.17

.(\

1.15

POSITIVE LOGITS

1.64

1.46

т

1.45

 legitim

1.42

 sanit

1.39

↵

1.38

 conex

1.32

 revital

1.29

 promo

1.28

 jeopard

1.28

Activations Density 0.000%