INDEX

Explanations

self, identity, existence

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

ទំន

0.44

 tones

0.42

 banter

0.41

 hábito

0.40

 atteggi

0.40

 আনার

0.38

 teorie

0.38

 भरोसे

0.38

 भक्ति

0.37

 theories

0.37

POSITIVE LOGITS

 identity

1.59

 identidad

1.37

identity

1.34

 Identity

1.34

Identity

1.30

 identidade

1.27

 identities

1.23

 IDENTITY

1.21

 existence

1.20

身份

1.19

Activations Density 0.054%