INDEX

Explanations

pokémon, androids, enemies, malicious intent

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

руем

1.12

Benzoimidazol

1.07

 Pronto

1.04

্ধ্য

1.02

 bbox

0.99

 або

0.99

 производи

0.97

 toán

0.95

 수행

0.95

Rx

0.95

POSITIVE LOGITS

 condemning

1.45

 trolls

1.27

ي

1.17

 baddies

1.16

 condemn

1.13

ల

1.11

 بتق

1.10

killers

1.09

ths

1.09

 enemy

1.06

Activations Density 0.001%