INDEX

Explanations

teaching and teachings

training

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

 theorist

0.65

RIER

0.60

せ

0.59

 tabled

0.59

 assassination

0.58

 fleshy

0.58

 comprobar

0.56

EOUT

0.56

 şeklinde

0.56

 unlocks

0.56

POSITIVE LOGITS

Teaching

0.75

는

0.73

خ

0.71

 dạy

0.68

教

0.67

 Teaching

0.66

在

0.66

สอน

0.65

ع

0.64

teaching

0.63

Activations Density 1.328%