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

    Neuronpedia

    INDEX
    Explanations

    references to various forms of crime and criminal activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.81
     Ibarra
    -0.71
     Erickson
    -0.70
    bohemian
    -0.67
    ="<?=
    -0.66
     extérieurs
    -0.65
     bénéficiaire
    -0.65
    انجليز
    -0.64
    //
    -0.63
     fratelli
    -0.63
    POSITIVE LOGITS
     crime
    2.17
     Crime
    2.13
    Crime
    2.00
     CRIME
    1.91
     crimes
    1.90
     Crimes
    1.82
    crime
    1.76
    crimes
    1.53
     crimen
    1.24
    Cri
    1.06
    Act Density 0.053%

    No Known Activations