INDEX

Explanations

agents and potential

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Negative Logits

 Obviously

1.01

obviously

0.96

Obviously

0.93

 unquestionably

0.92

 obviamente

0.91

 evidentemente

0.87

<unused1612>

0.87

<unused851>

0.85

 évidemment

0.84

 obviously

0.84

POSITIVE LOGITS

style

0.82

EU

0.81

 style

0.78

sub

0.76

전

0.76

 sustainable

0.76

রা

0.74

 flexible

0.74

전

0.74

Sa

0.73

Activations Density 0.609%

No Known Activations