INDEX

Explanations

"this" followed by new context

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

juč

1.63

그러나

1.61

бні

1.61

Namun

1.59

 تاہم

1.56

 "{!}

1.55

 }{}_{\

1.54

 Tetapi

1.53

لیکن

1.52

ErrMsg

1.52

POSITIVE LOGITS

 horrible

1.12

1.07

guy

1.06

 crap

1.03

0.99

cre

0.96

 perp

0.96

 tini

0.96

 gotta

0.94

Activations Density 0.336%