INDEX

Explanations

gods and deities

The neuron activates on words referring to gods or deities (e.g., god, gods, deity, deities, pantheon).

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

他已经

-2.00

屜

-1.77

などが

-1.73

[]>(

-1.70

不一样的

-1.66

龉

-1.66

tolsó

-1.63

但他

-1.58

というわけで

-1.57

."

-1.56

POSITIVE LOGITS

of

2.19

are

1.85

1.80



1.73

 gods

1.68

 later

1.65

 paziente

1.64

aimeJ

1.64

 abbraccio

1.64

可能

1.63

Activations Density 0.020%