INDEX

Explanations

pronouns followed by actions or states

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

 avete

1.93

它

1.90

그리고

1.86

 то

1.80

 diketahui

1.79

 pozorn

1.78

 образом

1.77

 erythematosus

1.76

 фонд

1.75

 tuổi

1.74

POSITIVE LOGITS

<bos>

1.85

of

1.83

ik

1.73

HIB

1.71

ed

1.67

cence

1.66

 akin

1.65

িক

1.63

zelfde

1.62

 tantamount

1.61

Activations Density 0.258%