INDEX

Explanations

the word "depicted."

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

No Comments

Negative Logits

 liggen

-0.76

nhung

-0.74

Schwe

-0.73

Samantha

-0.73

ChildScrollView

-0.71

Samoa

-0.71

umbledore

-0.69

 gambe

-0.69

 nắm

-0.68

lüğü

-0.68

POSITIVE LOGITS

 depict

1.04

 depicts

0.95

 depicting

0.94

BeginContext

0.87

 depicted

0.87

PGC

0.86

 depiction

0.85

 depictions

0.84

########.

0.77

 phong

0.75

Activations Density 0.005%