INDEX

Explanations

normalization of behaviors or rules

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

 viability

2.09

ness

2.02

ive

1.94

ство

1.90

ך

1.89

یت

1.87

 достижения

1.83

 tides

1.81

 ligero

1.72

ियों

1.69

POSITIVE LOGITS

aciji

2.05

𝘦

1.95

ли

1.89

︎

1.87

된

1.85

1.84

ד

1.82

ти

1.81

об

1.80

ין

1.78

Activations Density 0.196%