INDEX

Explanations

parentheses and formulas

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

2.02

ן

1.83

ның

1.76

おか

1.76

ना

1.73

 качества

1.72

%@",

1.72

एं

1.71

lah

1.71

lage

1.66

POSITIVE LOGITS

2.05

লিখিত

1.58

 Frankly

1.53

тную

1.51

ीय

1.48

์

1.45

 Jeho

1.43

 brimming

1.41

 argue

1.41

1.40

Activations Density 0.040%