INDEX

Explanations

expressing gratitude

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

 パネル

-0.92

Bt

-0.89

 beträ

-0.84

وسی

-0.81

 одном

-0.81

 върху

-0.80

 credibility

-0.80

 явля

-0.80

𝜔

-0.78

關於

-0.78

POSITIVE LOGITS

 thankful

1.70

 grateful

1.51

 thanking

1.48

 thanked

1.38

for

1.37

 agradec

1.34

 Thanksgiving

1.30

 Thanks

1.21

 gratitude

1.20

 agrade

1.20

Activations Density 0.005%