INDEX

Explanations

asking about specific years

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

চ

2.47

autorité

2.43

 unary

2.31

 cura

2.26

 bille

2.20

 Umum

2.19

在

2.19

ت

2.18

 rasgos

2.18

логия

2.17

POSITIVE LOGITS

गिर

2.07

CrossOrigin

2.02

rnd

1.93

ned

1.92

leşt

1.89

lings

1.89

Leak

1.87

nc

1.86

 olds

1.84

ling

1.82

Activations Density 0.074%