INDEX

Explanations

human characteristics and cognition

This neuron detects occurrences of the word “human” (and its plural form).

New Auto-Interp

Configuration

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

ون

1.57

al

1.27

وين

1.26

د

1.22

gleich

1.13

ام

1.13

ör

1.13

ார்

1.10

giv

1.10

POSITIVE LOGITS

 beings

1.52

 umana

1.38

ير

1.36

적으로

1.26

 manusia

1.23

з

1.23

 humana

1.22

ן

1.20

১৯

1.18

 Anthrop

1.18

Activations Density 0.021%