INDEX

Explanations

oddity and strangeness

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

Sexy

0.40

 beğ

0.40

Idea

0.36

 హీరో

0.35

 तहे

0.35

 thrilled

0.34

 दहशत

0.34

uldade

0.33

gató

0.33

liğini

0.33

POSITIVE LOGITS

 strange

2.28

odd

2.17

 interesting

1.97

 peculiar

1.97

 curious

1.91

strange

1.90

 стран

1.82

 weird

1.81

 unusual

1.79

 Strange

1.77

Activations Density 0.094%