INDEX

Explanations

No Explanations Found

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

យ៉ាង

0.72

็ว

0.57

 pona

0.57

廝

0.55

 ganske

0.55

 행동

0.54

لمات

0.53

 effectually

0.53

膾

0.53

 puissant

0.53

POSITIVE LOGITS

 sense

2.72

sense

2.23

 Sense

2.08

Sense

1.95

 senso

1.63

 sentido

1.49

 penchant

1.28

 tendency

1.25

 feeling

1.24

 willingness

1.21

Activations Density 1.232%

No Known Activations