INDEX

Explanations

specified relation words

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

-1.29

zyć

-0.91

だから

-0.89

やはり

-0.88

ależ

-0.88

alnız

-0.88

 colch

-0.87

of

-0.86

警方

-0.85

}');

-0.84

POSITIVE LOGITS

 vergeten

1.07

 رضا

1.02

 emozioni

1.01

ﺅ

1.00

 zufrieden

0.97

 gezwungen

0.96

を変更

0.96

 sinnvoll

0.96

кона

0.93

ătoare

0.93

Activations Density 0.262%