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

    Neuronpedia

    INDEX
    Explanations

    references to legal proceedings and law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    mentions of prosecutors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.76
    oken
    -0.73
    forward
    -0.72
    lihood
    -0.71
    omach
    -0.70
    birth
    -0.69
    patch
    -0.68
    wo
    -0.66
    eem
    -0.66
    opic
    -0.64
    POSITIVE LOGITS
     prosecutor
    0.92
     prosecutors
    0.90
     indicted
    0.88
     investigator
    0.88
    heet
    0.86
     investigating
    0.81
     allege
    0.79
     prosecuted
    0.79
     subpoen
    0.78
     oun
    0.78
    Act Density 0.016%

    No Known Activations