INDEX

Explanations

assigning values in code

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

and

-3.11

for

-2.52

any

-1.99

 this

-1.96

by

-1.89

if

-1.81

 with

-1.77

or

-1.77

at

-1.73

 which

-1.72

POSITIVE LOGITS

沵

1.66

 acclaimed

1.64

 expliquer

1.60

 indiquer

1.59

 stockfoto

1.55

 arrêter

1.55

 FOUR

1.53

forgot

1.49

 AMAZING

1.48

 REALLY

1.45

Activations Density 0.006%