INDEX

Explanations

numbers and symbols

language signaling severe harm or abuse—e.g., explicit slurs, sexual violence/exploitation terms, and other highly offensive or harmful content.

New Auto-Interp

Configuration

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

1.09

daki

1.07

dı

1.06

tól

1.06

dna

0.95

ten

0.93

tt

0.89

depth

0.88

nama

0.88

gable

0.87

POSITIVE LOGITS

是

0.92

는

0.88

ih

0.76

ี่

0.75

</h3>

0.74

</strong>

0.70

<0x0D>

0.68

</em>

0.67

ీ

0.66

Α

0.65

Activations Density 0.553%