INDEX

Explanations

probability distributions and functions

The neuron activates on occurrences of the word “exponential” (e.g. exponential distributions, exponential functions, exponential moving average).

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

 alcune

-1.15

ほとん

-1.14

щите

-1.13

 xadrez

-1.13

 siè

-1.12

 afront

-1.09

 grandiose

-1.07

 palha

-1.06

ellants

-1.06

 japan

-1.03

POSITIVE LOGITS

 with

1.83

 will

1.36

 their

1.30

on

1.25

1.24

for

1.24

 model

1.23

we

1.20

our

1.17

as

1.16

Activations Density 0.065%