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

    Neuronpedia

    INDEX
    Explanations

    references to violent crimes and murder

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    murder or killing

    np_acts-logits-general · gemini-2.0-flash

    violent murder and sexual crimes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.77
    DoubleQuotes
    -0.69
     kasarigan
    -0.69
    )))));
    -0.68
    ContentAsync
    -0.68
    })$}
    -0.66
    ")));
    -0.65
    "}")
    -0.62
    ablanca
    -0.61
    spreis
    -0.61
    POSITIVE LOGITS
     murders
    0.86
     murder
    0.83
     murderer
    0.76
     homicide
    0.75
     killings
    0.73
     crimes
    0.72
     homic
    0.72
     murdered
    0.70
     Murder
    0.70
     crime
    0.70
    Act Density 0.337%

    No Known Activations