INDEX

Explanations

changing and replacing text

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

 může

0.80

 może

0.80

 nearing

0.80

 muere

0.79

 quedaría

0.79

 mogą

0.78

 obsahuje

0.77

 inducing

0.74

жить

0.73

 ['',

0.73

POSITIVE LOGITS

 took

1.99

Took

1.87

took

1.84

 Took

1.79

 went

1.77

Started

1.75

Changed

1.75

 gave

1.74

 Removed

1.71

 Gave

1.71

Activations Density 0.321%