INDEX

Explanations

accusations and allegations

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

蘊

0.75

⊙

0.70

 interessant

0.68

://

0.68

 Circulation

0.67

ත්ම

0.66

 intéressante

0.65

 interesting

0.64

நாயக

0.64

ઠી

0.62

POSITIVE LOGITS

 accusations

3.50

 accusation

3.41

 allegations

3.15

 allegation

3.14

 accuse

3.02

 accused

3.01

 accuses

2.83

 accusing

2.64

 обви

2.51

 acusado

2.34

Activations Density 0.113%