INDEX

Explanations

asking about something

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

дий

0.68

是一位

0.67

énération

0.64

κή

0.63

silyl

0.63

breve

0.61

indeki

0.60

ücks

0.60

новні

0.59

वंशी

0.59

POSITIVE LOGITS

 things

4.52

 something

4.29

 thing

4.07

 anything

4.05

things

3.81

 Things

3.77

something

3.73

 Something

3.70

 cosas

3.60

 everything

3.55

Activations Density 1.917%