INDEX

Explanations

be a descriptor

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

年は

1.56

 disusun

1.48

 contamos

1.44

 calendario

1.44

 organización

1.43

astia

1.40

spraak

1.39

タック

1.39

organizzazione

1.39

 calendário

1.38

POSITIVE LOGITS

 violently

2.41

 uncontroll

2.17

 faintly

2.05

 смер

2.04

 combust

2.02

 rage

2.02

 softly

2.01

了起来

1.97

着

1.96

 sensation

1.95

Activations Density 0.783%