INDEX

Explanations

regardless of condition

The neuron is specifically detecting occurrences of the word “regardless.”

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

</b>

-2.72

了一個

-1.85

などを

-1.67

-1.61

 proverbial

-1.57

</h1>

-1.56

 einige

-1.48

时机

-1.44

 продаж

-1.43

POSITIVE LOGITS

of

2.50

Ꭳ

2.13

，“

2.13

鐿

2.02

whether

1.96

 spiele

1.92

 zelve

1.90

 whether

1.89

祆

1.84

theres

1.82

Activations Density 0.007%