Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of accusations and charges in a criminal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Families
    -0.13
    jÃł
    -0.13
     Author
    -0.13
     Created
    -0.13
    mpp
    -0.12
    ä¸Ģä¸ĭ
    -0.12
    á»īnh
    -0.12
     Pulitzer
    -0.12
    éf
    -0.12
    Author
    -0.11
    POSITIVE LOGITS
     age
    0.34
     aged
    0.30
     male
    0.26
     residing
    0.25
    -age
    0.25
     resident
    0.24
     unemployed
    0.23
     ages
    0.23
     Age
    0.23
     homeless
    0.23
    Act Density 0.071%

    No Known Activations