INDEX

Explanations

import

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

__":

-0.88

__':

-0.82

 '\\;'

-0.75

})();

-0.75

 onOptions

-0.71

TemporalType

-0.71

__":

-0.68

})));

-0.68

posedge

-0.65

 EconPapers

-0.65

POSITIVE LOGITS

RIP

0.54

squareup

0.51

xase

0.50

RIP

0.48

Aliens

0.45

struktion

0.44

Author

0.43

 Ausland

0.43

 unre

0.43

 Author

0.42

Activations Density 0.060%