INDEX

Explanations

progression after "to"

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

-2.44

if

-2.08

↵↵↵

-1.73

is

-1.72

to

-1.69

 única

-1.69

<td>

-1.62

 إذا

-1.59

<bos>

-1.58

</td>

-1.55

POSITIVE LOGITS

笮

2.23

 résistant

2.00

GillaGilla

1.98

 antworte

1.95

⛦

1.95

1.90

 vexed

1.89

 opérés

1.85

 Gespräche

1.85

⎆

1.84

Activations Density 0.003%