INDEX

Explanations

waiting for

The neuron activates on the concept of waiting—i.e. occurrences of “wait,” “waiting,” “await,” “awaiting,” and related forms.

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

Surprisingly

-2.08

Following

-1.91

</h2>

-1.81

.\\

-1.80

-1.72

-1.70

Another

-1.67

 raccol

-1.66

Again

-1.60

驹

-1.60

POSITIVE LOGITS

</u>

2.41

</i>

2.19

嗵

1.87

我们

1.80

 opravdu

1.80

鶿

1.74

ING

1.70

)=>{

1.68

ꪹ

1.66

 espera

1.66

Activations Density 0.025%