INDEX

Explanations

stop followed by instruction or consequence

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

Бы

1.97

Д

1.67

 transpired

1.63

それで

1.60

ღვ

1.59

 दिलीप

1.55

 destructor

1.55

Основ

1.54

直し

1.54

 افز

1.53

POSITIVE LOGITS

tı

2.39

tır

2.09

ى

2.05

tat

1.93

ő

1.92

ur

1.91

ranges

1.80

etition

1.78

ip

1.77

tedir

1.77

Activations Density 0.028%