INDEX

Explanations

mathematical symbols and unicode

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

equ

1.34

1.32

パクト

1.31

erb

1.27

able

1.27

oja

1.27

er

1.26

 синте

1.26

 belles

1.25

ه

1.25

POSITIVE LOGITS

<0x92>

1.86

<0xA6>

1.52

 eğer

1.45

 countless

1.40

<0xAB>

1.38

<0x94>

1.37

ensity

1.37

GÁ

1.37

<0x93>

1.36

 plummeted

1.35

Activations Density 0.008%