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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal convictions

    oai_token-act-pair · gpt-3.5-turbo

    references to legal convictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebus
    -0.77
    ÃŁ
    -0.76
    hod
    -0.75
    eton
    -0.71
    hens
    -0.71
    hy
    -0.71
    gm
    -0.71
    esta
    -0.70
    yss
    -0.68
    opter
    -0.67
    POSITIVE LOGITS
     convictions
    1.02
     conviction
    0.94
    eering
    0.91
    icts
    0.77
     overturned
    0.77
    alties
    0.76
    iction
    0.75
     convict
    0.74
     convicted
    0.74
     warrant
    0.74
    Act Density 0.017%

    No Known Activations