INDEX

Explanations

introduces agency or method

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

ية

0.80

ized

0.70

gunaan

0.64

ר

0.62

기

0.62

ado

0.61

 keresztül

0.61

 utilização

0.61

elolaan

0.60

ين

0.57

POSITIVE LOGITS

and

0.79

 একজন

0.63

 یک

0.60

 virtue

0.58

서는

0.58

AND

0.57

 पर्दे

0.57

 μια

0.56

Activations Density 0.082%