INDEX

Explanations

reportedly, allegedly, criticised

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

 your

1.38

 আপনার

1.31

your

1.25

 שלך

1.22

 항상

1.21

you

1.20

 당신

1.19

 അവന്റെ

1.18

 உங்கள்

1.17

)!

1.14

POSITIVE LOGITS

 reportedly

2.31

 allegedly

1.78

 criticised

1.77

 criticized

1.76

 allegations

1.71

 alleged

1.66

 largely

1.66

 purportedly

1.65

 critics

1.59

 ostensibly

1.56

Activations Density 0.492%