INDEX

Explanations

national followed by institute name

The neuron selectively activates on occurrences of the word “National” (typically in organization or study names).

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

The

-1.91

This

-1.84

いただいて

-1.73

 When

-1.58

-1.56

 This

-1.55

すると

-1.45

If

-1.42

Their

-1.42

 then

-1.41

POSITIVE LOGITS

 ananas

1.60

洇

1.52

 damen

1.52

 alip

1.52

茕

1.51

 Irland

1.48

 tertawa

1.48

 inger

1.45

 entusias

1.43

 kollu

1.42

Activations Density 0.085%