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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of honor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     verſ
    -0.66
    <unused15>
    -0.66
    -0.66
    BSITE
    -0.66
     queſta
    -0.65
    <unused57>
    -0.65
     queſto
    -0.65
    <unused27>
    -0.65
     fashiola
    -0.65
    -0.64
    POSITIVE LOGITS
    Hon
    1.66
     honor
    1.59
     Hon
    1.59
     honour
    1.55
    hon
    1.55
     honoured
    1.50
     honored
    1.50
     hon
    1.45
     honors
    1.44
     HON
    1.43
    Act Density 0.210%

    No Known Activations