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

    Neuronpedia

    INDEX
    Explanations

    instances where someone has been convicted of a crime

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals being convicted of crimes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.76
    abwe
    -0.75
    mentation
    -0.72
    arity
    -0.71
    hare
    -0.70
    eah
    -0.68
    ankind
    -0.67
    earable
    -0.67
    aven
    -0.66
    idge
    -0.66
    POSITIVE LOGITS
     felon
    0.96
    icts
    0.82
     guilty
    0.82
     convict
    0.78
    iary
    0.77
     convicted
    0.75
     perjury
    0.74
     unfocusedRange
    0.72
     debtor
    0.70
     judge
    0.69
    Act Density 0.023%

    No Known Activations