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

    Neuronpedia

    INDEX
    Explanations

    the beginning of new sections or significant transitions in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    󠁢
    -0.56
    ielle
    -0.53
    nables
    -0.51
    terday
    -0.50
    bain
    -0.47
    lenme
    -0.47
    itee
    -0.47
    ileen
    -0.47
    ͐
    -0.47
     peines
    -0.46
    POSITIVE LOGITS
    <bos>
    1.22
    LookAnd
    0.93
    GEBURTSDATUM
    0.77
    Autoritní
    0.76
    المشاركات
    0.76
    PYX
    0.74
    RTEE
    0.72
     iprot
    0.71
    InvalidProtocol
    0.69
    protoimpl
    0.68
    Act Density 0.857%

    No Known Activations