INDEX

Explanations

names starting with D or R

The neuron activates on personal names (proper nouns referring to individual people).

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

and

-2.17

gridColumn

-1.98

 your

-1.84

あなたは

-1.75

})->

-1.72

೬

-1.70

 falda

-1.69

かもし

-1.66

のですか

-1.65

 partid

-1.60

POSITIVE LOGITS

lohn

1.91

も

1.90

も多く

1.88



1.84

 ciudadana

1.73

 razões

1.69

 通过

1.67

 适合

1.67

brador

1.65

 chrétienne

1.63

Activations Density 0.098%