INDEX

Explanations

table followed by noun

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

 людини

0.96

е

0.95

 بالله

0.92

 boots

0.90

대

0.90

ش

0.88

wami

0.87

ן

0.83

paragraph

0.83

ajal

0.82

POSITIVE LOGITS

LayoutPanel

1.38

poon

1.29

 cerc

1.27

tennis

1.24

cloth

1.24

 teamTable

1.23

uleiro

1.16

ernacle

1.10

 स्पून

1.10

hôte

1.08

Activations Density 0.064%