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

    Neuronpedia

    INDEX
    Explanations

    words related to domestic issues or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to domestic issues and topics related to domestic violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uyomi
    -0.90
    uden
    -0.81
    */(
    -0.75
    SOURCE
    -0.75
    umper
    -0.74
    ombs
    -0.71
    veyard
    -0.69
    UMP
    -0.68
    Magikarp
    -0.67
    displayText
    -0.67
    POSITIVE LOGITS
     Violence
    0.93
     tranqu
    0.92
     affairs
    0.90
     violence
    0.89
     appliances
    0.83
    estic
    0.76
     spying
    0.76
     combustion
    0.76
    violence
    0.75
     terrorism
    0.72
    Act Density 0.024%

    No Known Activations