INDEX

Explanations

code snippets and structure

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

ط

1.82

knife

1.67

л

1.65

ю

1.58

로

1.56

finished

1.55

es

1.54

adic

1.51

danger

1.50

level

1.48

POSITIVE LOGITS

ін

2.04

 notably

1.94

𝐗

1.80

 gazed

1.78

மேலும்

1.77

smanship

1.76

}<\

1.76

𝙩

1.74

ahanglan

1.72

фика

1.71

Activations Density 0.000%