INDEX

Explanations

local + terms like optima, variables, minimum, video, list, length

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

ますが

2.50

ل

2.31

تها

2.27

ين

2.19

ש

2.19

で

1.98

िट

1.87

ます

1.85

ière

1.84

们

1.81

POSITIVE LOGITS

 apice

1.83

cuda

1.82

 optima

1.77

 hins

1.73

 afferma

1.73

cuss

1.71

 commenc

1.71

1.70

 πάντα

1.69

 setempat

1.68

Activations Density 0.048%