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

    Neuronpedia

    INDEX
    Explanations

    numeric values and their associated formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     arşivlendi
    -0.63
    RectangleBorder
    -0.59
     الكه
    -0.51
    herjee
    -0.50
    ẵng
    -0.50
    ритори
    -0.49
     nødvendig
    -0.49
    Hozzáférés
    -0.49
    avigation
    -0.49
    Tembelea
    -0.48
    POSITIVE LOGITS
    <bos>
    0.69
     للمعارف
    0.60
    __":
    0.59
     testator
    0.57
    Filmografie
    0.55
    évaluateur
    0.53
     appellant
    0.52
    ofday
    0.49
     <=",
    0.49
    最快更新
    0.49
    Act Density 0.058%

    No Known Activations