INDEX

Explanations

like

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 zijne

-0.76

,‎

-0.66

 eenige

-0.64

 dezelve

-0.57

 hänen

-0.57

 argint

-0.57

 mensuales

-0.57

 occupé

-0.56

 hunne

-0.56

 dentaire

-0.56

POSITIVE LOGITS

 transfieras

0.84

 صوتيه

0.67

NHS

0.66

principalTable

0.64

tenham

0.63

########.

0.60

nhs

0.59

 loads

0.59

NHS

0.58

 binh

0.58

Activations Density 0.008%