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

    Neuronpedia

    INDEX
    Explanations

    tokens that represent numerical data or parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.90
     himo
    -0.68
    twimg
    -0.68
    oneofs
    -0.64
    TagMode
    -0.64
     oprot
    -0.62
    pośred
    -0.61
     newOwner
    -0.61
     تضيفلها
    -0.60
    vember
    -0.60
    POSITIVE LOGITS
     './../
    0.69
     /\.
    0.61
     /\.(
    0.61
    ]!='
    0.60
    ','',
    0.60
    =".
    0.60
    ={({
    0.59
    arkas
    0.58
    "]').
    0.58
    }'.
    0.57
    Act Density 0.075%

    No Known Activations