INDEX

Explanations

North

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

tonsoft

-0.72

AxisAlignment

-0.71

UnusedPrivate

-0.67

 يتيمه

-0.66

titleMargin

-0.65

rostis

-0.61

 negative

-0.60

 تانيه

-0.59

 שוליים

-0.58

сылкі

-0.58

POSITIVE LOGITS

 épaules

0.56

WireFormatLite

0.51

 GenerationType

0.49

 oreilles

0.48

 blessés

0.45

cork

0.45

oa̍t

0.45

 soldati

0.44

mybatisplus

0.44

:+:

0.43

Activations Density 0.005%