INDEX

Explanations

"so i", "this is", "I have"

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

㉕

-2.09

:”

-2.02

 grossen

-1.97

した

-1.90

 یا

-1.86

 eigentlichen

-1.74

 prodot

-1.73

л

-1.70

っている

-1.69

乄

-1.64

POSITIVE LOGITS

2.38

2.17

},

2.03

‐

1.85

reurs

1.70

*,

1.67

1.63

archiwizowane

1.60

FORMANCE

1.59

1.55

Activations Density 0.057%