INDEX

Explanations

evaluating positivity

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

 disadvantage

0.42

 ciem

0.42

 desvent

0.39

Dark

0.39

DARK

0.38

с

0.37

 DARK

0.36

 Squid

0.36

Compact

0.35

コンパクト

0.35

POSITIVE LOGITS

 positive

1.34

Positive

1.22

positive

1.20

 Positive

1.20

 pozitiv

1.13

 सकारात्मक

1.09

 положи

1.09

 positivo

1.08

 positif

1.06

 positivos

1.06

Activations Density 1.706%