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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating greater significance or value relative to others

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     noqa
    -0.69
     houſe
    -0.67
     Houſe
    -0.67
     againſt
    -0.65
     оригіналу
    -0.62
    neſs
    -0.61
     pngtree
    -0.60
     ſou
    -0.60
    MessageOf
    -0.59
     miſ
    -0.58
    POSITIVE LOGITS
    nodoc
    0.53
     exceeding
    0.47
    icoot
    0.47
     превы
    0.46
    httphttps
    0.45
     exceeds
    0.44
    Assista
    0.43
     alia
    0.43
    cheidet
    0.43
     bilhões
    0.43
    Act Density 0.063%

    No Known Activations