INDEX

Explanations

avoiding frustration or aggression

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

 அதிசய

0.72

神经网络

0.72

 Vermeer

0.68

 אור

0.68

𝄞

0.67

 लागे

0.67

AppCompat

0.67

безпе

0.67

 WorldCat

0.66

ocyte

0.66

POSITIVE LOGITS

 anger

2.57

 angry

2.53

 angrily

2.13

 rage

2.13

 aggressive

2.11

 enraged

2.11

 aggression

2.09

 hostility

1.97

 fury

1.95

 angered

1.92

Activations Density 1.936%