INDEX

Explanations

multi-part, multi-modal, multi-layered

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

nw

0.80

 Mostrar

0.71

әк

0.70

 adopted

0.69

 Certain

0.69

гө

0.68

 certain

0.68

Certain

0.68

術

0.67

 কাপড়

0.67

POSITIVE LOGITS

faceted

1.44

layered

1.39

 sclerosis

1.34

pronged

1.33

 myeloma

1.25

 layered

1.22

 faceted

1.21

plicity

1.17

 prong

1.17

 sided

1.14

Activations Density 0.169%