INDEX

Explanations

gendered humans and objects

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

 person

0.53

人

0.46

 persons

0.46

Person

0.46

Persons

0.44

person

0.42

persons

0.42

PERSON

0.41

사람

0.41

ssss

0.40

POSITIVE LOGITS

 Assurance

0.42

 assure

0.39

 assurance

0.37

thousand

0.37

ច្រ

0.35

 тыся

0.35

udahan

0.35

resos

0.34

thias

0.34

 വ്യ

0.34

Activations Density 0.032%