INDEX

Explanations

references to sexual harassment

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

 jsPsych

-0.82

NewGuid

-0.66

 doInBackground

-0.66

InstanceState

-0.63

 Chim

-0.62

 Paglinawan

-0.61

InjectAttribute

-0.60

>>>>>>>>

-0.59

VYMaps

-0.57

mability

-0.56

POSITIVE LOGITS

 harassment

3.25

 harass

2.69

 Harassment

2.55

 harassing

2.50

 harassed

2.44

assment

1.83

 acoso

1.51

 bullying

0.79

 bullied

0.72

 persecution

0.71

Activations Density 0.003%