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

    Neuronpedia

    INDEX
    Explanations

    phrases related to different forms of abuse and violence inflicted on individuals

    oai_token-act-pair · gpt-3.5-turbo

    themes of abuse and violence, particularly in relation to personal and social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ciation
    -0.73
    aldo
    -0.67
     IPM
    -0.66
    brainer
    -0.66
    nostic
    -0.65
    URI
    -0.65
    ossibility
    -0.63
    imum
    -0.63
    BSD
    -0.61
    urai
    -0.61
    POSITIVE LOGITS
     perpetrated
    0.78
     dealings
    0.75
     perceived
    0.73
     portrayed
    0.71
     minorities
    0.71
     previous
    0.71
     lately
    0.71
     supposedly
    0.70
     preceding
    0.69
     administrations
    0.67
    Act Density 0.899%

    No Known Activations