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

    Neuronpedia

    INDEX
    Explanations

    expressions relating to societal norms and beliefs that are taken for granted

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wikiseite
    -0.76
    الإنجليزية
    -0.53
    subpackage
    -0.52
    jenige
    -0.51
    calo
    -0.50
     pauvre
    -0.49
    propTypes
    -0.49
    isamment
    -0.48
    createServer
    -0.48
    ůž
    -0.47
    POSITIVE LOGITS
     guaranteed
    1.00
     automatic
    0.99
     unquestion
    0.99
     själ
    0.98
     obvious
    0.95
     évidence
    0.94
     indisputable
    0.93
     inevitable
    0.93
     undisputed
    0.91
     inevit
    0.87
    Act Density 0.360%

    No Known Activations