INDEX

Explanations

"never" in different languages

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 propOrder

-0.85

expandindo

-0.74

 snippetHide

-0.70

 otomatig

-0.66

parsedMessage

-0.66

 Previously

-0.63

లాలు

-0.62

Хьажоргаш

-0.60

jooq

-0.58

 Others

-0.58

POSITIVE LOGITS

 never

2.36

never

1.91

 Never

1.72

Never

1.69

 NEVER

1.55

 nunca

1.49

NEVER

1.38

 nigdy

1.32

 aldrig

1.30

 nooit

1.30

Activations Density 0.000%