INDEX

Explanations

curved displays, contrastive learning, spacetime curvature

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

ли

1.52

ęcie

1.32

]='

1.27

ﺭ

1.19

hö

1.12

ğe

1.11

ಾಂಶ

1.11

<0x80>

1.09

दुर्ग

1.08

 konusunda

1.07

POSITIVE LOGITS

1.70

ों

1.55

 दौरान

1.42

ের

1.39

Этот

1.39

Ар

1.33

არ

1.30

cluding

1.30

 ГӀ

1.28

doped

1.26

Activations Density 0.001%