INDEX

Explanations

past tense verbs describing actions, consequences, or states

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

 stanno

0.76

 ہے۔

0.72

 están

0.70

ходят

0.70

 ہیں۔

0.70

 हैं

0.69

 করিতেছেন

0.69

 pracuje

0.68

 fanno

0.67

 येतात

0.66

POSITIVE LOGITS

was

1.32

 était

1.30

 ήταν

1.22

 była

1.17

 थी

1.10

 была

1.10

 było

1.08

 buvo

1.07

이었다

1.06

 vardı

1.05

Activations Density 0.017%