INDEX

Explanations

verbs indicating joining or leaving

The neuron strongly activates on numeric quantity tokens (especially numbers or measurements, often with decimal points).

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

 them

-1.22

新たに

-1.19

-1.18

-1.16

ać

-1.14

当你

-1.13

环节

-1.13

她們

-1.12

お前

-1.07

 képes

-1.07

POSITIVE LOGITS

大多

1.23

 necessario

1.13

rcs

1.12

iit

1.10

 blanches

1.10

нился

1.09

íž

1.06

 начать

1.06

 iniz

1.05

ittarius

1.04

Activations Density 0.105%