INDEX

Explanations

be careful with sensitive topics

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

 മികച്ച

0.92

 excelencia

0.92

 satisfacer

0.90

 avantages

0.89

简洁

0.88

 endlich

0.86

 đạt

0.85

 avantaj

0.82

 kebutuhan

0.81

 bättre

0.81

POSITIVE LOGITS

 excessive

1.10

 sensitive

1.08

 improperly

1.07

 excessively

1.05

 unsafe

1.04

 unauthorized

1.03

 harmful

1.02

 overly

1.01

 suspicious

1.01

 questionable

1.01

Activations Density 1.051%