INDEX

Explanations

much followed by comparatives

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

en

1.88

 packed

1.83

𝓽

1.78

 fooling

1.76

های

1.75

scrollTo

1.73

𝓻

1.72

miot

1.71

 crushing

1.70

pOt

1.69

POSITIVE LOGITS

લી

1.78

ї

1.57

问题

1.56

ように

1.49

ある

1.48

()=>{

1.47

方法

1.45

→</

1.44

து

1.41

ról

1.40

Activations Density 0.119%