INDEX

Explanations

extracting specific data

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

ंधन

1.77

 crucifixion

1.71

 embarrassment

1.69

 Atal

1.66

जीलैंड

1.64

 Цуки

1.63

 hurry

1.62

Ν

1.59

GOR

1.58

 izquierda

1.57

POSITIVE LOGITS

as

2.46

и

1.83

сь

1.72

 откуда

1.71

ا

1.70

 количестве

1.61

पति

1.61

is

1.59

Activations Density 0.187%