INDEX

Explanations

list type attribute properties object

This neuron fires on occurrences of the term “list” (often as part of code identifiers or APIs) in programming code.

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

 จาก

-1.54

zionali

-1.51

tabolism

-1.49

ribune

-1.49

 маленький

-1.45

岽

-1.45

茘

-1.45

 "-";

-1.44

↵↵

-1.43

 lèvres

-1.41

POSITIVE LOGITS

2.53

。"

2.00

.,"

1.93

....

1.83

='

1.73

不愧

1.65

 assistenza

1.62

...."

1.61

人性

1.61

('

1.60

Activations Density 0.028%