INDEX

Explanations

location prepositions followed by nouns

The main thing this neuron does is detect prepositions and locative markers (like “in,” “at,” “on,” “here,” etc.) that introduce locations or spatial contexts.

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

-1.95

-1.70

<h2>

-1.69

-1.67

 also

-1.63

for

-1.60

 always

-1.60

</h2>

-1.60

-1.59

-1.57

POSITIVE LOGITS

咘

1.59

engelsk

1.54

Seperti

1.51

الج

1.51

 deportivos

1.51

komt

1.46

涐

1.45

鋅

1.45

Жизнь

1.43

Ketika

1.41

Activations Density 0.059%