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

    Neuronpedia

    INDEX
    Explanations

    references to geographic locations and administrative divisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     która
    -0.58
     jakie
    -0.54
     została
    -0.51
     která
    -0.51
     jotka
    -0.50
     którzy
    -0.48
     quella
    -0.48
     ktorá
    -0.47
    those
    -0.47
     jaką
    -0.47
    POSITIVE LOGITS
    čený
    0.69
    vaný
    0.68
     derselbe
    0.63
    žený
    0.63
    ższy
    0.60
    bný
    0.59
    ický
    0.59
    towany
    0.59
    ský
    0.58
    ený
    0.57
    Act Density 0.117%

    No Known Activations