INDEX

Explanations

working followed by functional noun

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

</b>

1.03

</h3>

1.00

</strong>

0.99

기

0.94

ש

0.93

</h2>

0.91

ال

0.88

كان

0.88

</h4>

0.86

POSITIVE LOGITS

 working

1.05

ة

0.94

 Working

0.90

 WORKING

0.84

ون

0.83

ми

0.80

 مثال

0.79

 trabajando

0.77

 कामकाजी

0.76

۔

0.76

Activations Density 0.011%