INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<unused1916>

1.46

<unused578>

1.43

oughs

1.38

<unused1229>

1.37

<unused1798>

1.37

 überw

1.35

<unused340>

1.35

<unused1713>

1.33

<unused189>

1.33

<unused992>

1.32

POSITIVE LOGITS

 logic

0.94

 sana

0.93

mal

0.92

sol

0.90

Sol

0.87

 magic

0.83

 fame

0.83

PA

0.82

 cosa

0.81

 thằng

0.80

Activations Density 0.053%

No Known Activations