INDEX

Explanations

sports games

The neuron strongly activates on occurrences of the word “game” (and closely related match- or sports-event terms).

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>

-1.88

-1.81

-1.73

↵

-1.62

-1.58

who

-1.55

</h1>

-1.53

since

-1.48

 patienter

-1.44

 ваше

-1.42

POSITIVE LOGITS

mucha

1.46

 tomadas

1.42

nume

1.39

pkey

1.38

чики

1.37

迨

1.37

 حتی

1.36

any

1.36

而去

1.33

MIO

1.33

Activations Density 0.012%