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

    Neuronpedia

    INDEX
    Explanations

    references to people and their roles or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     noastre
    -0.63
     itſelf
    -0.61
     debió
    -0.59
    platte
    -0.59
    itself
    -0.57
     للاسماء
    -0.57
     ProductService
    -0.56
    isies
    -0.55
     Itself
    -0.55
    likasi
    -0.54
    POSITIVE LOGITS
     who
    1.22
     whom
    1.19
    whom
    0.95
    who
    0.90
    Whom
    0.83
     quien
    0.79
     Who
    0.79
     którzy
    0.77
     кто
    0.70
     quienes
    0.69
    Act Density 0.166%

    No Known Activations