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

    Neuronpedia

    INDEX
    Explanations

    expressions related to violence and violent behavior

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.91
     noDo
    -0.71
     Schuyler
    -0.70
    NOPQRST
    -0.70
     sembler
    -0.67
    quelize
    -0.66
     guava
    -0.63
    essment
    -0.63
    zzang
    -0.63
     >=",
    -0.63
    POSITIVE LOGITS
     violence
    1.20
     Violence
    1.16
    violence
    1.07
     Violent
    1.07
    Violent
    0.97
    Violence
    0.96
    violent
    0.96
     violen
    0.95
     violent
    0.94
     VIOL
    0.88
    Act Density 0.005%

    No Known Activations