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

    Neuronpedia

    INDEX
    Explanations

    elements that indicate numbers or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <?
    -0.65
    spesies
    -0.59
    ⓧ
    -0.58
    談社
    -0.57
     Мексичка
    -0.54
     nahilalakip
    -0.53
    Izvori
    -0.51
    rouvez
    -0.51
    -0.50
    Glej
    -0.49
    POSITIVE LOGITS
     
    1.41
    2
    1.01
    3
    0.88
    1
    0.87
    4
    0.79
    5
    0.76
    7
    0.75
    6
    0.72
    8
    0.71
    9
    0.68
    Act Density 0.325%

    No Known Activations