INDEX

Explanations

terrifying, horrifying, devastating

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

rás

1.17

 Denne

1.05

 Erst

1.02

ermost

0.98

 egiten

0.97

 చేసే

0.97

enskap

0.97

쫑

0.96

grund

0.96

ausible

0.96

POSITIVE LOGITS

 assaults

1.20

柅

1.18

 monstrous

1.17

 алге

1.14

 terrifying

1.13

ISTER

1.08

 horrifying

1.08

正则表达式

1.07

 devastating

1.07

 insanely

1.06

Activations Density 0.002%