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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments or adverse effects associated with medical or technological topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kaiser
    -0.51
     vệ
    -0.50
     sisters
    -0.47
     Boyle
    -0.47
    ITHUB
    -0.45
    arsen
    -0.44
     vista
    -0.44
     Sisters
    -0.44
    heder
    -0.44
     Dobson
    -0.44
    POSITIVE LOGITS
    setVerticalGroup
    0.82
    Personendaten
    0.77
     ModelExpression
    0.73
     للاسماء
    0.71
    Personensuche
    0.71
    ⓧ
    0.70
    TagMode
    0.70
     חיצוניים
    0.69
    twimg
    0.69
    sizeCache
    0.68
    Act Density 0.026%

    No Known Activations