INDEX

Explanations

the word "trigger"

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.96

 ―――――

-0.91

 Benth

-0.86

ագրություններ

-0.85

 itſelf

-0.84

nexo

-0.83

 Braw

-0.83

 russes

-0.81

 Forumite

-0.81

 sauvages

-0.80

POSITIVE LOGITS

 trigger

1.59

 Trigger

1.50

 triggers

1.48

 Triggers

1.47

trigger

1.45

Trigger

1.41

triggers

1.39

Triggers

1.34

TRIGGER

1.33

 triggering

1.20

Activations Density 0.006%