INDEX

Explanations

missing and exploited children

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

 atta

0.40

療法

0.39

тке

0.39

 structs

0.37

 হেসে

0.37

िटर

0.36

 dies

0.36

 संक्रम

0.36

羟

0.35

 струк

0.35

POSITIVE LOGITS

 missing

1.59

 Missing

1.47

 disappearance

1.44

Missing

1.41

 लापता

1.41

missing

1.36

 desaparecido

1.28

 lost

1.25

 desapare

1.23

 disappeared

1.23

Activations Density 0.028%