INDEX

Explanations

films and awards

The neuron strongly responds to award‐related category and nomination terms (e.g. Best Picture, Best Actor, Supporting Actress, Director).

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

‚

-1.81

 других

-1.81

èles

-1.79

ཥ

-1.77

bilidad

-1.67

FundMe

-1.65

 другие

-1.63

 unſ

-1.60

utiva

-1.59

のように

-1.59

POSITIVE LOGITS

Also

1.95

1.86

 with

1.80

 thậm

1.76

1.72

There

1.61

If

1.55

This

1.49

--

1.48

With

1.44

Activations Density 0.073%