INDEX

Explanations

political rhetoric and conflict

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

 Typically

1.16

Typically

1.08

typically

1.01

 erstmal

0.95

0.91

 typically

0.89

0.88

 встроен

0.88

 subset

0.87

 ह्या

0.83

POSITIVE LOGITS

 slogans

1.35

 sectoral

1.27

 foreigners

1.26

 cooperation

1.26

 patriotism

1.24

 slander

1.23

 consultations

1.22

 shortcomings

1.21

 ideological

1.21

 conspiracies

1.18

Activations Density 0.003%