INDEX

Explanations

\

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 attrition

-0.77

 perpetuity

-0.75

 concatenation

-0.74

AutoresizingMask

-0.73

 senescence

-0.73

 incipient

-0.72

 interacted

-0.69

 homogeneity

-0.69

 Normdatei

-0.69

 pedagogy

-0.69

POSITIVE LOGITS

bad

0.41

bad

0.39

")(

0.39

')(

0.39

.].

0.37

Église

0.36

>(

0.36

 importanza

0.36

 wicked

0.35

].

0.35

Activations Density 0.000%