INDEX

Explanations

detonate, activate, influence

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

ної

1.55

க்

1.43

ت

1.43

িক

1.36

ोक

1.36

म

1.36

na

1.30

こちらの

1.27

йи

1.24

 dolphins

1.23

POSITIVE LOGITS

 ouvido

1.73

ferences

1.48

 descubre

1.48

centos

1.47

 Lomond

1.46

'{

1.43

្ខ

1.41

goers

1.41

mortem

1.40

 quidem

1.40

Activations Density 0.002%