INDEX

Explanations

references to wrestling or wrestlers

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

 Sport

-0.59

ברס

-0.57

 kred

-0.55

 sport

-0.55

 Paglinawan

-0.55

 sporty

-0.54

vieren

-0.52

 Sports

-0.51

 LEAF

-0.50

afl

-0.49

POSITIVE LOGITS

 wrestling

3.16

 Wrestling

3.03

 wrestler

2.70

 wrestle

2.70

Wrestling

2.67

 wrestled

2.56

 wrestlers

2.55

restling

2.23

 wrest

1.84

restle

1.77

Activations Density 0.001%