INDEX

Explanations

years and dates

The neuron flags numeric values that include decimal points (i.e. floating-point numbers).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

妧

-1.25

[{{

-1.22

]');

-1.22

 različ

-1.20

σσ

-1.14

%;

-1.14

GFR

-1.13

︕

-1.13

htiö

-1.13

 compati

-1.13

POSITIVE LOGITS

 only

1.59

for

1.59

if

1.56

 then

1.51

1.29

 more

1.28

 yılı

1.27

 around

1.23

 also

1.17

 because

1.15

Activations Density 0.104%