INDEX

Explanations

comes to

The neuron specifically detects the phrase “comes to” (i.e. the word comes followed by 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

Negative Logits

</i>

-2.11

");

-1.98

 všechny

-1.97

ంలో

-1.92

』。

-1.88



-1.88

特長

-1.86

)$.

-1.81

 músculos

-1.74

￪

-1.73

POSITIVE LOGITS

to

3.19

</strong>

2.27

ный

1.96

“

1.91



1.88

PostInfinity

1.83

”

1.83

il

1.82

 Then

1.80

you

1.77

Activations Density 0.006%