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

    Neuronpedia

    INDEX
    Explanations

    special sequence tokens or markers that signify the beginning of important sections in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BeginContext
    -0.77
    ⓧ
    -0.72
    CloseOperation
    -0.71
    userdetails
    -0.63
     Sancho
    -0.58
    __*/
    -0.57
     MainAxisSize
    -0.56
     informée
    -0.56
     الدولى
    -0.56
    EndContext
    -0.55
    POSITIVE LOGITS
     själva
    0.61
    cmake
    0.55
     بلکه
    0.52
     antaranya
    0.50
     dermed
    0.50
    afterEach
    0.49
    으며
    0.47
     nødvendig
    0.47
     dafür
    0.46
     Nor
    0.46
    Act Density 0.152%

    No Known Activations