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

    Neuronpedia

    INDEX
    Explanations

    terms related to domestic violence and abusive relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.86
    ethene
    -0.75
     riuscito
    -0.72
     τά
    -0.70
    ajuato
    -0.70
    arschijnlijk
    -0.70
     Stras
    -0.69
     ima
    -0.69
    imread
    -0.69
    grap
    -0.69
    POSITIVE LOGITS
     Domestic
    1.04
     domestic
    1.01
    Domestic
    0.97
    domestic
    0.96
     domesti
    0.86
    ESTIC
    0.86
     domestically
    0.81
    Household
    0.74
     household
    0.73
     ……………………
    0.72
    Act Density 0.165%

    No Known Activations