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

    Neuronpedia

    INDEX
    Explanations

    structured code elements and organizational structures in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.47
    <eos>
    -0.46
    aspectj
    -0.46
    pat
    -0.46
    AttributeSet
    -0.45
    char
    -0.44
    芥
    -0.43
    ory
    -0.43
     tu
    -0.41
    ống
    -0.41
    POSITIVE LOGITS
     houſe
    0.79
    harusnya
    0.75
     pleaſure
    0.73
    StructEnd
    0.69
    ousand
    0.68
     purpoſe
    0.68
     Walkover
    0.67
    Controllo
    0.67
    tidaknya
    0.65
     nahilalakip
    0.64
    Act Density 0.396%

    No Known Activations