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

    Neuronpedia

    INDEX
    Explanations

    references to societal classes and group identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.80
    клопе
    -0.69
     InputDecoration
    -0.68
    lapsingToolbar
    -0.65
    elemField
    -0.65
    aarrggbb
    -0.63
    ometra
    -0.62
    ValueStyle
    -0.61
    poons
    -0.60
    EnableWeb
    -0.60
    POSITIVE LOGITS
     who
    0.91
     whom
    0.87
     kteří
    0.76
     którzy
    0.71
     quienes
    0.70
    whom
    0.69
    who
    0.66
     privilégi
    0.65
     byli
    0.65
     individuals
    0.65
    Act Density 0.924%

    No Known Activations