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

    Neuronpedia

    INDEX
    Explanations

    specific numeric values and quantitative comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     referenties
    -0.71
     старости
    -0.64
    이버
    -0.62
    wijl
    -0.61
    󠁿
    -0.61
    Portail
    -0.58
     autorytatywna
    -0.58
     wikihow
    -0.58
     nhàng
    -0.58
     Portail
    -0.57
    POSITIVE LOGITS
    processable
    0.74
    ]='\
    0.72
    ffions
    0.71
    tvguidetime
    0.68
     {}".
    0.65
    Trả
    0.65
    ÁND
    0.64
    iffance
    0.64
    ſſen
    0.62
    æa
    0.61
    Act Density 0.998%

    No Known Activations