INDEX

Explanations

life in

The neuron strongly activates on mentions of the word “life” when it appears in the context of “life in…” (i.e. identifying phrases that describe life within a particular place or setting).

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

 because

-1.57

なんですが

-1.49

tagext

-1.47

なのですが

-1.45

sukienka

-1.43

getreten

-1.41

}}{\

-1.39

 никогда

-1.39

));

-1.38

 that

-1.36

POSITIVE LOGITS

 ayakkabı

1.62

 dezen

1.56

 ayakkab

1.52

1.51

1.49

not

1.43

1.41

 autres

1.38

的白

1.35

ž

1.35

Activations Density 0.030%