INDEX

Explanations

University graduations and affiliations

The neuron activates on mentions of “University” (i.e., instances of academic institution 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

of

-1.56

儛

-1.51

可能會

-1.51

纐

-1.47

either

-1.46

 Mereka

-1.46

 può

-1.45

imgnum

-1.44

不夠

-1.43

 ataupun

-1.41

POSITIVE LOGITS

1.55

 после

1.42

rageous

1.40

you

1.38

नलोड

1.36

%;

1.33

 vectoriales

1.32

嶋

1.31

ようやく

1.31

↵↵

1.31

Activations Density 0.041%