INDEX

Explanations

thresholds and critical values

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

拚

-1.65

however

-1.38

 präsenti

-1.34

 câte

-1.34

把她

-1.33

the

-1.29

 destul

-1.25

来到了

-1.24

 vraag

-1.23



-1.23

POSITIVE LOGITS

say

1.36

 затем

1.24

،

1.24

dzić

1.24

gning

1.23

)}}

1.22

));

1.19

$,

1.19

 sagen

1.17

 will

1.16

Activations Density 0.047%