INDEX

Explanations

statements with "apparently"

The neuron fires on occurrences of the hedging adverb “apparently,” especially when it begins a clause.

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>

-2.14

We

-1.78

your

-1.66

我們

-1.65

 skapa

-1.62

窃

-1.58

of

-1.57

offerta

-1.56

 limitée

-1.55

)_{

-1.54

POSITIVE LOGITS

が少ない

1.76

 längere

1.70

 😂

1.64

ポジ

1.56

Theres

1.55

 🤣

1.52



1.52

’;

1.48

,“

1.47

 there

1.46

Activations Density 0.015%