INDEX

Explanations

percentages

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

чего

1.62

arsipkan

1.56

置いて

1.56

ograp

1.55

 pausa

1.55

ŏ

1.54

تالي

1.54

sou

1.53

ческий

1.50

 suku

1.50

POSITIVE LOGITS

 completely

1.62

1.56

 ninety

1.51

 completamente

1.51

 totalmente

1.49

 totally

1.42

completely

1.40

 entirely

1.39

 entièrement

1.36

 wholly

1.35

Activations Density 0.209%