INDEX

Explanations

moral judgment and emotion

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

 일반적으로

1.07

Generally

1.05

 사용자

1.03

 সাধারণত

1.03

 أيضًا

1.03

一般来说

1.02

 suelen

1.02

 Generally

1.01

 많이

1.01

Selain

0.99

POSITIVE LOGITS

 resentment

1.19

 empathy

1.13

 hypocrisy

1.12

 dehuman

1.11

 arrogance

1.10

 humility

1.09

 metaphor

1.07

 selfishness

1.06

 retribution

1.06

 compassion

1.04

Activations Density 0.432%