INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 licencia

1.62

 relação

1.55

 Fuerza

1.55

僱

1.53

ating

1.52

 Fortsch

1.52

 contraceptive

1.51

 lysine

1.50

ມັນ

1.50

 Damit

1.48

POSITIVE LOGITS

极致

2.08

extent

1.98

 extent

1.97

ppling

1.92

いや

1.73

特色的

1.71

alek

1.67

◸

1.65

ppins

1.64

al

1.63

Activations Density 0.333%

No Known Activations