INDEX

Explanations

names following "my name is"

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

It

-1.85

なんか

-1.66

この日は

-1.66

 decidi

-1.61

Karakteristik

-1.59

༔

-1.58

-1.55

for

-1.54

Olvid

-1.54

慙

-1.53

POSITIVE LOGITS

},

1.79

và

1.77

wyn

1.73

 оружие

1.73

 лише

1.67

 also

1.64

 only

1.63

 stras

1.63

 και

1.63

and

1.63

Activations Density 0.009%