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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criminal convictions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals being convicted of crimes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arity
    -0.77
     RIS
    -0.66
    psey
    -0.65
    patch
    -0.63
    alter
    -0.63
    andel
    -0.62
    oos
    -0.62
    ww
    -0.62
    owa
    -0.61
    haar
    -0.61
    POSITIVE LOGITS
     convict
    0.90
     convicted
    0.89
     felon
    0.87
    icts
    0.81
     sentenced
    0.79
     convictions
    0.73
     unfocusedRange
    0.73
    iary
    0.72
     guilty
    0.72
    ctuary
    0.69
    Act Density 0.010%

    No Known Activations