INDEX

Explanations

pronoun followed by verb

The neuron detects personal subject pronouns (e.g., I, he, she, they).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

="

-1.91

 económicas

-1.87

-}

-1.84

 financieras

-1.83

あえず

-1.77

$+$

-1.71

'),

-1.69

 deportivas

-1.67

”、“

-1.66

$=$

-1.65

POSITIVE LOGITS

2.09

1.98

1.88

着一

1.69

1.62

 terá

1.61

焌

1.57

を使用

1.55

 same

1.53

着一个

1.48

Activations Density 0.059%