INDEX

Explanations

legal and illegal activities

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

ה

3.23

ل

2.67

ه

2.62

ссии

2.50

2.41

המ

2.40

śmy

2.38

le

2.33

া

2.22

or

2.21

POSITIVE LOGITS

ább

2.60

 marah

2.17

ड़ब

2.15

tais

2.14

nya

2.13

ských

2.08

breviations

2.07

itimate

2.07

 sausages

2.07

ivät

2.05

Activations Density 0.522%