INDEX

Explanations

mathematical expressions or formulas

+

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

Negative Logits

ulka

-0.59

期刊论文

-0.59

||}

-0.56

 dira

-0.55

)("

-0.54

.))

-0.52

ød

-0.51

uA

-0.51

arier

-0.50

пія

-0.50

POSITIVE LOGITS

2.27

>+</

2.16

}+

2.06

$+

2.06

$+\

2.00

()+

1.95

)+

1.93

}+\

1.92

$+$

1.90

Activations Density 3.633%