INDEX

Explanations

user profile

The neuron is highly responsive to mentions of a user’s “profile” (and its variants).

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

to

-1.55

-1.51

ábamos

-1.48

</i>

-1.48

皛

-1.42

 from

-1.38

鹮

-1.35

龅

-1.35

-1.34

POSITIVE LOGITS

ふう

1.69

┍

1.64

その他の

1.63

 vínculo

1.62

 dominar

1.61

その他

1.60

休日

1.55

 vacunas

1.55

 yerde

1.54

過去の

1.52

Activations Density 0.017%