INDEX

Explanations

introducing or describing something

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

InitStruct

1.01

나가

1.00

 Dona

1.00

َّا

0.99

 inviting

0.97

 satellite

0.97

 tightly

0.97

 benign

0.94

 Satellite

0.93

 enlarging

0.93

POSITIVE LOGITS

Tidak

1.53

tidak

1.47

篌

1.34

 સામે

1.31

 Tidak

1.30

ｨ

1.29

หนัง

1.28

ت

1.26

 tidak

1.26

iszt

1.25

Activations Density 0.001%